Split (1)

train · 8.3M rows

Search is not available for this dataset

conversations listlengths 2 2
[ { "from": "human", "value": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to concatenate all elements of A from the ith element to the jth element, and print the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n\n1, 6, ['U', '7765', '3049', '717', '115', '9317', '527', '5395', '3213', 'M', 'H', 'e', 'Y', 'z', '2749', '3439', 'l', 'P', '2265', '8841', '3629', '9295', 't', '277', '8633', '7255', 'H']\nU776530497171159317\n\n17, 19, ['6519', '9015', 'i', '3363', '8547', 'x', 'f', 'H', '5557', '2135', '1559', 'S', 'b', '4833', '7801', '7375', '3729', 'y', '8667', 'G', '7723', '4571', 'J', '1997', '8663', 'l', 'b', 'T']\n3729y8667\n\n2, 3, ['9249', '173', 'X', 'U', 'D', '4817', '2367', 'J', '2909', 'z', 's', '25', 'J']\n" }, { "from": "gpt", "value": "173X\n\n" } ]
[ { "from": "human", "value": "Languages typically provide more than one grammatical construction to express certain types of messages. Your task is to generate a senetence with the same meaning as given sentence, but with different grammatical construction.\n\nJuan broadcasted a man something" }, { "from": "gpt", "value": "Juan broadcasted something to a man" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task you are expected to provide an SQL statement from an english description of what that SQL statement does. The description may include multiple steps but you should only ouput one SQL statement that accomplishes every step. An SQL query works by selecting data from a table where certain conditions apply. A table contains columns where every row in that table must have a value for each column. Every table has a primary key that uniquely identifies each row, usually an id. To choose which columns are returned you specify that after the \"SELECT\" statement. Next, you use a \"FROM\" statement to specify what tables you want to select the data from. When you specify a table you can rename it with the \"AS\" statement. You can reference that table by whatever name follows the \"AS\" statement. If you want to select data from multiple tables you need to use the \"JOIN\" statement. This will join the tables together by pairing a row in one table with every row in the other table (Cartesian Product). To limit the number of rows returned you should use the \"ON\" statement. This will only return rows where the condition specified after the statement is true, this is usually an equals operator with primary keys. You can also use the \"WHERE\" statement to specify that only rows with column values statisfying a certain condition, should be returned. The \"GROUP BY\" statement will group rows together that have equal column values for whatever columns follows the statement. The \"HAVING\" statement will return groups that statisfy whatever condition follows the statement. Any column(s) being returned from grouped rows must either be an aggregate function, (AVG, MAX, COUNT, SUM, ...) of a column, or the column(s) that the data was grouped by. To sort the returned data you can use the \"ORDER BY\" command which will order the data by whatever aggregate function or column follows the statement. The \"DESC\" statement will sort in descending order and the \"ASC\" statement will sort in ascending order. Finally, you can use the \"LIMIT\" statement to return a certain number of rows. When \"\" is used in an SQL statement every column is returned. For example, SELECT FROM table WHERE attribute = 1, will select every column from rows with the attribute column equal to 1.\n\nStep 1: For each row in Students table, find the corresponding rows in Student_Course_Enrolment table.\nStep 2: find the number of rows of each value of Student_Course_Enrolment's student_id in the results of step 1.\nStep 3: find Student_Course_Enrolment's student_id, middle_name of step 1 results ordered descending by the results of step 2.\nStep 4: only show the first 2 rows of the results\n" }, { "from": "gpt", "value": "SELECT T2.student_id , T1.middle_name FROM Students AS T1 JOIN Student_Course_Enrolment AS T2 ON T1.student_id = T2.student_id GROUP BY T2.student_id ORDER BY Count ( * ) Desc LIMIT 2" } ]
[ { "from": "human", "value": "Instructions: Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].\nInput: ['hey', \"it's\", 'Becca', 'and', 'this', 'is', 'temperance', 'part', '2', 'and', 'in', 'this', 'video', \"I'll\", 'be', 'talking', 'more', 'about', 'how', 'exactly', 'over', 'the', 'course', 'of', 'the', '1830s', 'until', 'mostly', 'the', '1860s', 'the', 'temperance', 'movement', 'took', 'root', 'in', 'America', 'and', 'how', 'it', 'became', 'this', 'national', 'phenomenon', 'so', 'a', 'lot', 'of', 'it', 'had', 'to', 'do', 'with', 'temperance', 'societies', 'so', 'in', 'the', 'last', 'video', 'I', 'mentioned', 'that', 'the', 'American', 'Temperance', 'Society', 'was', 'founded', 'in', '1826', 'so', \"that's\", '1826', 'but', 'the', 'American', 'Temperance', 'Society', 'really', 'was', 'this', 'group', 'of', 'upper-class', 'northern', 'white', 'dudes', 'saying', 'oh', 'well', 'we', 'should', 'probably', 'make', 'sure', 'that', 'people', \"don't\", 'drink']\nOutput:" }, { "from": "gpt", "value": "['NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_AND_PUNCUATION_DIFF', 'CASE_DIFF', 'DIGIT_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_AND_PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_AND_PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_AND_PUNCUATION_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF']" } ]
[ { "from": "human", "value": "In this task if the pronoun is female or gender-neutral you are to replace it with a male pronoun. If there are no pronouns add a male-gendered word to the sentence.\n\nsorry to hear that. am bari by name. what's your name young lady?\nSorry to hear that. Am Bari by name. what's your name?\n\nwell, that woman was once a member of the house of commons in canada.\nWell, she was once a member of the House of Commons in Canada.\n\ngreat. I'll try to get christian kim's fashion for my husband soon. do you know him?\n" }, { "from": "gpt", "value": "Great. I'll try to get Christian Kim's fashion for my wife there soon. Do you know her?\n\n" } ]
[ { "from": "human", "value": "In this task, You are given a review of Amazon's food products. Your task is to divide them into two classes: negative or positive, depending on the content of the review.\n\nLet me give you an example: These are junk! Both bulbs have burned out within a two month period!! I cannot believe that this company can be in business with such poor quality. I have used infrared lights for my ball python for many years now and I get a varied range of months from a bulb, but I have never gone through two bulbs in a matter of two months! I am very disappointed.\nThe answer to this example can be: negative\nHere is why: The user seems very disappointed in the product. Because the bulb they ordered has been burned out earlier than usual. So, it's a negative review.\n\nOK. solve this:\nBroken & extremely flimsy! It was smaller than stated, (2\" less in length), I could tell the minute I saw it. VERY flimsy materials! I cannot believe I paid $24 for this! (My $10, dollar store bag was far better quality than this one!). One zipper is already BROKEN the first time I tried to unzip it! I can tell the other zippers won't last the upcoming 5-day trip. Now I have to travel to the next town to purchase ANOTHER bag at WalMart, which are less $$ and better quality. WHAT A RIP-OFF!\nAnswer:" }, { "from": "gpt", "value": "negative" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a review from Amazon and your task is to generate the name of the category of the product based on the review given by the user. The categories are: kitchen, office product, watch, wireless, other, toy, digital video download, camera, jewelry, pet products, sports, industrial supplies, baby product, grocery, drugstore, home improvement, pc, shoes, automotive, digital ebook purchase, musical instruments, beauty, book, electronics, lawn and garden, apparel, home, video games, luggage, furniture, personal care appliances.\nSee one example below:\nProblem: Arrived broken. Manufacturer defect. Two of the legs of the base were not completely formed, so there was no way to insert the casters. I unpackaged the entire chair and hardware before noticing this. So, I'll spend twice the amount of time boxing up the whole useless thing and send it back with a 1-star review of part of a chair I never got to sit in. I will go so far as to include a picture of what their injection molding and quality assurance process missed though. I will be hesitant to buy again. It makes me wonder if there aren't missing structures and supports that don't impede the assembly process.\nSolution: furniture\nExplanation: The customer gives a review of the product which belongs to the furniture category because we can see it from the way the customer describes his experience sharing how he unpackaged his chair.\n\nProblem: I just got it so can't say how long it will last however the diffuser is flat which means when drying my curls of course they flatten from the air and can't be cupped by the diffuser. I should have caught that in the picture. The cool-shot doesn't work so I have to change settings. You get what you pay for on this one.\nSolution:" }, { "from": "gpt", "value": "beauty" } ]
[ { "from": "human", "value": "Detailed Instructions: Given a document, generate a short title of the document. The title should convey the main idea/event/topic about which the document is being written. Note that URLs in the text have been replaced with [Link].\nQ: \"He used to appear invincible \" McDowell noted after he delivered two brilliant clutch putts and beat Woods at the first hole of sudden death at Sherwood Country Club on Sunday.\n Plenty of talk swirled around Woods in 2010 and much of it had less to do with his golf game than with the revelations of marital infidelity that exploded in November of 2009.\n By August his marriage was over he had lost millions in endorsement deals and for the first time since he turned pro Woods finished a season without a victory.\n But Woods admitted that the off-course turmoil affected him and he also struggled to get to grips with the swing changes he was implementing with coach Sean Foley.\nTiger Woods' bid to end a tumultuous year with a victory at his World Challenge fell short but Graeme McDowell predicted the US star will again be a dominant force in golf - and soon.\n \"He used to appear invincible \" McDowell noted after he delivered two brilliant clutch putts and beat Woods at the first hole of sudden death at Sherwood Country Club on Sunday.\n \"Of course he has made himself appear more human in the last 12 months... But there's something a bit special about his golf game and I fully expect that mystique to return as the golf clubs start doing the talking again.\"\n Plenty of talk swirled around Woods in 2010 and much of it had less to do with his golf game than with the revelations of marital infidelity that exploded in November of 2009.\n By August his marriage was over he had lost millions in endorsement deals and for the first time since he turned pro Woods finished a season without a victory.\n He played only 15 stroke-play events worldwide and got a nod as a captain's pick for the US Ryder Cup team.\n But Woods admitted that the off-course turmoil affected him and he also struggled to get to grips with the swing changes he was implementing with coach Sean Foley.\n A storming singles triumph on the last day of the Ryder Cup as well as a six- under final round at the Australian Masters in November were signs that his game was coming together.\n But it wasn't until this week that Woods was able to put it together for multiple rounds.\n \"I've played well in stretches now the stretches are lasting longer \" Woods said. \"It was just a few holes and then it became nine holes. First day it was all 18 holes.\n \"So it was progress ... I'm just really excited about this off-season \" Woods added. \"I haven't been that way in a while.\"\nA:" }, { "from": "gpt", "value": "Golf: Woods will dominate again - McDowell" } ]
[ { "from": "human", "value": "Teacher:In this task, you will be shown a sentence, and you should determine whether it is overruling or non-overruling. In law, an overruling sentence is a statement that nullifies a previous case decision as a precedent by a constitutionally valid statute or a decision by the same or higher ranking court which establishes a different rule on the point of law involved. Classify your answers into overruling or non-overruling\nTeacher: Now, understand the problem? Solve this instance: stowers had a full and fair opportunity to litigate his contempt in those proceedings, all the way through appeal to our court.\nStudent:" }, { "from": "gpt", "value": "non-overruling" } ]
[ { "from": "human", "value": "Q: In this task, you're given a pair of sentences, sentence 1 and sentence 2, that neither agree with nor contradict each other. Your job is to alter sentence 2 so that the pair clearly agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\nSentence 1: An older man is drinking orange juice at a restaurant. Sentence 2: A man in a restaurant is waiting for his meal to arrive.\nA:" }, { "from": "gpt", "value": "A man is drinking juice." } ]
[ { "from": "human", "value": "Definition: In this task, you're given a review from Amazon and category of the product based on the review given by the user and your task is classify whether the given category match the review. Generate \"True\" if given review and its category match, otherwise generate \"False\".\nInput: Reviews: Unfortunately I was never able to try them. My husband ordered these colors and the clear ones for me before Christmas, but they were not well packaged & were broken and a shattered mess when they were delivered. :( \n Category: drugstore\nOutput:" }, { "from": "gpt", "value": "True" } ]
[ { "from": "human", "value": "Instructions: Provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are coarse labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e tagset of this corpus is - \n '.': Period symbol is used for symbols denoting Punctuations/Separations such as comma, period, backticks etc., \n 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, \n 'ADP': Adposition is a cover term for prepositions and postpositions, \n 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, \n 'CONJ': A word used to connect clauses or sentences or to coordinate words in the same clause, \n 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, \n 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, \n 'NUM': A numeral is a word, functioning most typically as a determiner, adjective or pronoun, that expresses a number and a relation to the number, such as quantity, sequence, frequency or fraction, \n 'PRT': Particles are function words that must be associated with another word or phrase to impart meaning and that do not satisfy definitions of other universal parts of speech, \n 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, \n 'PROPN': A proper noun is a noun (or nominal content word) that is the name (or part of the name) of a specific individual, place, or object, \n 'VERB': A verb is a member of the syntactic class of words that typically signal events and actions, can constitute a minimal predicate in a clause, and govern the number and types of other constituents which may occur in the clause, \n 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.\nInput: Sentence: While *-1 acknowledging 0 {{ one }} month 's figures do n't prove a trend , Mr. Bretz said , `` It does lead you to suspect 0 imports are going down , or at least not increasing that much . '' \nWord: one\nOutput:" }, { "from": "gpt", "value": "NUM" } ]
[ { "from": "human", "value": "Given a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. For commands, 'left' and 'right' are used to denote the direction of an action. opposite turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. Actions and commands do not have quotations in the input and output.\n\n[Q]: I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_WALK I_TURN_RIGHT I_TURN_RIGHT I_WALK\n[A]: turn around right twice and walk opposite right twice\n\n\n[Q]: I_RUN I_RUN I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT\n[A]: run twice and turn around right thrice\n\n\n[Q]: I_TURN_RIGHT I_RUN I_TURN_RIGHT I_JUMP\n[A]:" }, { "from": "gpt", "value": "jump right after run right\n\n\n" } ]
[ { "from": "human", "value": "Q: In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to classify the command into one of these seven categories: (1) majority, (2) unique, (3) superlative, (4) count, (5) comparative, (6) aggregation, and (7) ordinal. \n Here are the defications of each category: \n 1. majority: Describing the majority values (most or all) over one column, with the scope of all table rows or a subset of rows \n 2. unique: Describing one unique row, regarding one column, with the scope of all table rows or a subset of rows \n 3. Superlative: Describing the maximum or minimum value in a column, with the scope of all table rows or a subset of rows \n 4. Ordinal: Describing the n-th maximum or minimum value in a column, with the scope of all table rows or a subset of rows \n 5. Comparative: Comparing two rows in the table, regarding their values in one column \n 6. Count: counting some rows in the table based on the values in one column, with the scope of all table rows or a subset of rows \n 7. Aggregation: Describing the sum or average value over a column, with the scope of all table rows or a subset of rows. \n Here are the definitions of logical operators for understanding of command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\nand { only { filter_eq { all_rows ; 2010 ; 12 } } ; eq { hop { filter_eq { all_rows ; 2010 ; 12 } ; tournament } ; win - loss } }\nA:" }, { "from": "gpt", "value": "unique" } ]
[ { "from": "human", "value": "Adverse drug reactions are appreciably harmful or unpleasant reactions resulting from an intervention related to the use of medical products, which predicts hazard from future administration and warrants prevention or specific treatment, or alteration of the dosage regimen, or withdrawal of the product. Given medical case reports extracted from MEDLINE, the task is to classify whether the case report mentions the presence of any adverse drug reaction. Classify your answers into non-adverse drug event and adverse drug event.\nOne example is below.\nQ: A case is reported of a child with fatal pulmonary fibrosis following BCNU therapy.\nA: adverse drug event\nRationale: Here, the child is facing some trouble after undergoing a particular therapy, thereby causing an adverse effect of the therapy.\nQ: Visual changes, headache, and elevated blood pressures were present on arrival to the emergency department.\nA:" }, { "from": "gpt", "value": "non-adverse drug event" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you're given the title of a five-sentence story and the first four sentences. Your job is to write the last sentence of the story to not connect with the rest of the story. Ensure that the generated sentence is contextually relevant to the story.\n\nTitle: Brad's car dies. Sentence 1: Brad was driving down the highway. Sentence 2: He started to hear a ticking noise in the engine. Sentence 3: His car started to smoke. Sentence 4: He decided to pull over on the side of the road.\n" }, { "from": "gpt", "value": "I returned home after 2 years 1 month and 24 days." } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGiven a passage with a context and an answer, construct a question on the basis of the information present in the passage. Construct the question in such a way that (i) it is unambiguous, (ii) it is answerable from the passage, (iii) its answer is unique (iv) it answer uses text phrases from the passage. Avoid creating questions that (i) can't be answered correctly without actually understanding the passage and (ii) uses the same words or phrases given in the passage.\n\nContext: Peroxisome proliferator activated receptor gamma (PPARgamma) is expressed in epithelial cells, macrophage, and T and B lymphocytes. Ligand induced activation of PPARgamma was reported to attenuate colitis activity but it is not clear whether this protection is mediated by epithelial or leucocyte PPARgamma.', 'Mice with targeted disruption of the PPARgamma gene in intestinal epithelial cells, generated using a villin-Cre transgene and floxed PPARgamma allele and designated PPARgamma(DeltaIEpC), were compared with littermate mice having only the PPARgamma floxed allele with no Cre transgene that expressed PPARgamma in the gut, designated PPARgamma(F/F). Colitis was induced by administering dextran sodium sulphate (DSS) and the two mouse lines compared for typical symptoms of disease and expression of inflammatory cytokines.', 'PPARgamma(DeltaIEpC) mice displayed reduced expression of the PPARgamma target genes ADRP and FABP in the gut but were otherwise normal. Increased susceptibility to DSS induced colitis, as defined by body weight loss, colon length, diarrhoea, bleeding score, and altered histology, was found in PPARgamma(DeltaIEpC) mice in comparison with PPARgamma(F/F) mice. Interleukin (IL)-6, IL-1beta, and tumour necrosis factor alpha mRNA levels in colons of PPARgamma(DeltaIEpC) mice treated with DSS were higher than in similarly treated PPARgamma(F/F) mice. The PPARgamma ligand rosiglitazone decreased the severity of DSS induced colitis and suppressed cytokine production in both PPARgamma(F/F) and PPARgamma(DeltaIEpC) mice.\nAnswer: These studies reveal that PPARgamma expressed in the colonic epithelium has an endogenous role in protection against DSS induced colitis and that rosiglitazone may act through a PPARgamma independent pathway to suppress inflammation.\nOutput:" }, { "from": "gpt", "value": "Does peroxisome proliferator activated receptor gamma in colonic epithelial cells protect against experimental inflammatory bowel disease?" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, you're given an article and an answer. Your task is to generate the fill-in-the-blank question for this answer based on the given article. The blanks are always at the end of the question, and can be filled with more than one word or phrase.\nPROBLEM: Article: Like the Five Olympic Rings from which they draw their color and inspiration, the Five Friendlies will serve as the Official Mascots of Beijing 2008 Olympic Games, carrying a message of friendship and peace and blessings from China to children all over the world. Designed to express the playful qualities of five little children who form an intimate circle of friends, the Five Friendlies also embody the natural characteristics of four of China's most popular animals--the Fish, the Panda, the Tibetan Antelope, the Swallow--and the Olympic Flame. Each of the Friendlies has a rhyming two-syllable name--a traditional way of expressing affection for children in China. Beibei is the Fish, Jingjing is the Panda, Huanhuan is the Olympic Flame, Yingying is the Tibetan Antelope and Nini is the Swallow. When you put their names together--Bei Jing Huan Ying Ni--they say \"Welcome to Beijing,\" offering a warm invitation that reflects the mission of the Five Friendlies as young ambassadors for the Olympic Games. The Five Friendlies also embody both the landscape and the dreams and aspirations of people from every part of the vast country of China. In their origins and their headpieces, you can see the five elements of nature--the sea, forest, fire, earth and sky--all stylistic rendered in ways that represent the deep traditional influences of Chinese folk art and ornamentation. \n Answer: blessing\n\nSOLUTION: The Official Mascots of Beijing 2008 Olympic Games carry the following messages EXCEPT _ .\n\nPROBLEM: Article: Are you sitting down?In that case,you should probably stand up before reading this. In the first advice of its kind,British experts are recommending office workers stand for at least two hours. day,in a warning against the dangers of prolonged sitting .The,idelines were developed by a group of experts invited by Public Health England and an advocacy up and were published online Monday in Sports Medicine. Compared to those of smoking,people who sit the most have more than twice the risk of developing Type 2 diabetes and cardiovascular disease,.a 13 percent increased risk of cancer and a 17 percent increased risk of premature death ,compared to those who sit the least. \"Even if you're meeting your physical activity guidelines,you cannot get rid of the risks of prolonged sitting,\"said Uavin Bradley,director of the campaign group Get Britain Standing,one of the authors of the new guidance .Bradley,who spoke during a telephone interview while walking,said officials figure out the average Briton sits for more than half of their working hours.His group is expanding its campaign to other countries including the U.S.on Tuesday and is pushing for more people to have access to a desk that allows them to stand. \"Companies should reconsider the culture around taking regular breaks and think about whether meetings could be held standing up or walking,\"said Bradley.\"We've sat on this problem for far too long\" \n Answer: .advocate people to stand more\n\nSOLUTION: The passage is mainly written to _ *\n\nPROBLEM: Article: It was the first snow of winter -- an exciting day for every child but not for most teachers. Up until now, I had been old enough to dress myself, but today would need some help. Miss Finlayson, my kindergarten teacher, had been through brst snow days many times, but I think she may still remember this one. I managed to get into my wool snow trousers. But I struggled won my jacket because it didn't fit well. It was a hand-mc-down from my brother, and if made me wonder why I had to wear his ugly clothes, At least my hat and scarf were mine, and they were quite pretty. Finally it was time to have Miss Finlayson help me with my boots . In her calm, motherly voice she said, \"By the end of winter, you will all be able to put on your own boots.\" I didn't realize at the at the time that this was more a statement of hope than of confidence . I handed her my boots and stuck out my foot. Like most children, I expected grown-ups to do all the work. After much pushing, she managed to get first one into place and then, with a sigh, worked the second one on too. I announced, \"They're on the wrong feet.\" She struggled to get the boots off and went through the joyless task of putting them on again. \"They're my brother's boots, you know,\" I said. \"I hate them\". Somehow, from long years of practice, she managed to act as though I wasn't an annoying little girl, She struggle with me, she asked, \"Now, where are your mittens ?\" I looked into her eyes and said, \"I didn't want to lose them, so I hid them in the toes of my boots. \n Answer: hat\n\nSOLUTION:" }, { "from": "gpt", "value": "The little girl was more satisfied with her _ .\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.\nProblem:We acquired the data in two rounds of annotation. In the first one, we were looking for original and uncommon sentence change suggestions.\nSolution:" }, { "from": "gpt", "value": "How do they introduce language variation?" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you are given two lists A,B. Find the longest common subsequence in the lists A and B.\nPart 2. Example\n[5797, 8817, '8297', 'b', 'U', 'b'], [5843, 8809, '8297', 'b', 'W', 'C']\nAnswer: 8297, b\nExplanation: Here, '8297, b' is the longest common subsequence in both the input lists [5797, 8817, '8297', 'b', 'U', 'b'] and [5843, 8809, '8297', 'b', 'W', 'C'].\nPart 3. Exercise\n[9469, 8117, 'I', 1049, 6153, 'L', 1465, 9935, '857', '4275', 'O', '3819', '4873', 'p', '8971', 'E', '3587', '4115', '1407', '5177', 'b', 'T', '111', 'z', 'z', '7879', 't', 'h', 'G', 'M', 'r', 6565, 'g', 'A'], [8843, 'R', 1387, 'U', '857', '4275', 'O', '3819', '4873', 'p', '8971', 'E', '3587', '4115', '1407', '5177', 'b', 'T', '111', 'z', 'z', '7879', 't', 'd', 'X', 'R', 'A', 'P', 3527, 'D', 9207, 8179, 'G']\nAnswer:" }, { "from": "gpt", "value": "857, 4275, O, 3819, 4873, p, 8971, E, 3587, 4115, 1407, 5177, b, T, 111, z, z, 7879, t" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you are given a multiple-choice question and you have to pick the correct option. Answer with option indexes (i.e., \"A\", \"B\", \"C\", and \"D\").\n\nPlant cells can't perform photosynthesis (A) in a backyard (B) in a desert (C) in a closet (D) in water\n" }, { "from": "gpt", "value": "C" } ]
[ { "from": "human", "value": "In this task, you are given a list. This list contains many lists of integers. The list is several items written within a []. Your task is to find the maximum number among the members of each inner list. The output should be a list comprised of the maximums with the same order as the internal lists.\n\nEx Input:\n[[-12, -101, -7, 46, 65, 60], [75, -187, -156], [21, -196], [-172, -42, -137, -90, 82, -85, 10], [4, -48, -50], [-3, -132], [-54, -23, 21]]\n\nEx Output:\n[65, 75, 21, 82, 4, -3, 21]\n\n\nEx Input:\n[[-176, 36, 94, 7, 55, 29], [-66, 24, -23, -199, -43, -40], [-99, -187, -132, -129, 12]]\n\nEx Output:\n[94, 24, 12]\n\n\nEx Input:\n[[5, 56], [-32, -191], [5, -174, -126, 1], [-111, -7, -102, -131]]\n\nEx Output:\n" }, { "from": "gpt", "value": "[56, -32, 5, -7]\n\n\n" } ]
[ { "from": "human", "value": "Decide the language of that sentence. The language can be English, French, German, Italian, or Spanish.\n\nExample input: Text: 'try and ehm go as close to ravine as possible but up towards the carved stones'.\nExample output: English\nExample explanation: This is an English sentence.\nQ: Text: 'it's level with the cr-- the falls'\nA:" }, { "from": "gpt", "value": "English" } ]
[ { "from": "human", "value": "In this task, you are given a sentence and a profession. The sentence mentions two professions: one's gender is identifiable using the coreference link with gendered pronouns and the other's gender is unidentifiable. You are expected to return whether the given profession's gender is identifiable or unidentifiable.\n\nSentence: The tailor saw the mechanic and explained him the price.\n Profession: mechanic" }, { "from": "gpt", "value": "Identifiable" } ]
[ { "from": "human", "value": "Definition: In this task, you need to count the number of vowels (letters 'a', 'e', 'i', 'o', 'u') / consonants (all letters other than vowels) in the given sentence.\nInput: Sentence: 'a cake made to look like two trains'. Count the number of consonants in the given sentence.\nOutput:" }, { "from": "gpt", "value": "15" } ]
[ { "from": "human", "value": "In this task you will be given a list of integers. For every element in the list, if the element is positive you should multiply it by 2. If the element is negative you should multiply it by -3. The output should be a list of integers that is the result of applying that logic to the input list.\n Note: A list is presented with comma separated numbers inside two brackets.\n\n[Q]: [-18, -74, -99, -63, 25, 37, 4, 96, 22, -3, -85]\n[A]: [54, 222, 297, 189, 50, 74, 8, 192, 44, 9, 255]\n\n\n[Q]: [-88, -76, 17, -7, -76]\n[A]: [264, 228, 34, 21, 228]\n\n\n[Q]: [61, -17, -59, 76, -51, 20, -35, -16, 65]\n[A]:" }, { "from": "gpt", "value": "[122, 51, 177, 152, 153, 40, 105, 48, 130]\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you need to provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are coarse labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e tagset of this corpus is - \n '.': Period symbol is used for symbols denoting Punctuations/Separations such as comma, period, backticks etc., \n 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, \n 'ADP': Adposition is a cover term for prepositions and postpositions, \n 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, \n 'CONJ': A word used to connect clauses or sentences or to coordinate words in the same clause, \n 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, \n 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, \n 'NUM': A numeral is a word, functioning most typically as a determiner, adjective or pronoun, that expresses a number and a relation to the number, such as quantity, sequence, frequency or fraction, \n 'PRT': Particles are function words that must be associated with another word or phrase to impart meaning and that do not satisfy definitions of other universal parts of speech, \n 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, \n 'PROPN': A proper noun is a noun (or nominal content word) that is the name (or part of the name) of a specific individual, place, or object, \n 'VERB': A verb is a member of the syntactic class of words that typically signal events and actions, can constitute a minimal predicate in a clause, and govern the number and types of other constituents which may occur in the clause, \n 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.\nProblem:Sentence: The work's two movements , one melodically sentimental , the other brightly capricious , are clever enough in a Ravel-like style , but they rehash {{ a }} wornout idiom . \nWord: a\nSolution:" }, { "from": "gpt", "value": "DET" } ]
[ { "from": "human", "value": "Teacher:Given an abstract, indicate which of the provided candidate titles (Option1 and Option2) best describes it (respond with the text of the title, not option1/2).\nTeacher: Now, understand the problem? Solve this instance: Abstract: A prospective study was made of 119 children with transient synovitis or any other cause for synovial effusion and elevated intra-articular pressure. During a follow-up of one year not one case of Perthes' disease was diagnosed and the late clinical and radiographic changes were minimal with moderate overgrowth of the femoral head in 33% and widening of the joint space in 14.2%. Our results do not support the widely accepted concept that Perthes' disease develops as a result of the period of elevated intra-articular pressure found in transient synovitis. Further research into this and Perthes' disease should follow the premise that they are two different diseases without any aetiological connection. \n Which is the apt title for the abstract? option1: Transient synovitis and Perthes' disease. Is there an aetiological connection? option2: Plastic bronchitis.\nStudent:" }, { "from": "gpt", "value": "Transient synovitis and Perthes' disease. Is there an aetiological connection?" } ]
[ { "from": "human", "value": "In this task, you're given a short article. Your job is to classify the article based on its category. Use the following classification labels, 0. World, 1. Sports, 2. Business, 3. Science or Technical. Label the text \"0\" if it contains information related to world. Label the text \"1\" if it contains information related to sports. Label the text \"2\" if it contains information related business. Label the text \"3\" if it contains science or technical related information. \n\nNo. 2 Oklahoma Rolls Over Kansas, 41-10 (AP) AP - Jason White threw for 389 yards and four touchdowns against a defense geared up to stop Adrian Peterson, and No. 2 Oklahoma defeated Kansas 41-10 on Saturday.\n1\n\nUS Airways, pilots to resume talks US Airways Group Inc. and its pilots union agreed to resume negotiations on wage and benefits cuts the carrier is seeking to operate during bankruptcy protection.\n2\n\nOil Jumps 5 Pct on Cold, Bin Laden Threat Oil prices surged 5 percent on Friday as frigid weather lingered in the mammoth US Northeast heating oil market and militant Osama bin Laden urged renewed attacks on Middle East oil installations.\n" }, { "from": "gpt", "value": "2\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given an open-domain question. Your task is to provide an answer to the given question. There is only one unique answer for each question. Your answer should be short, and refer to an entity, date, number, etc. Do not put your answer in the context of a sentence.\nQ: When was saudi arabia admitted to united nations?\nA:" }, { "from": "gpt", "value": "24 October 1945" } ]
[ { "from": "human", "value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2. Sentence 2 contradicts sentence 1. Your job is to alter sentence 2 so that the pair neither agree nor contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\n\nExample Input: Sentence 1: A man is holding his cup while he grills hotdogs. Sentence 2: a mouse runs along the floor.\nExample Output: A man sips his cocktails while he grills at the neighborhood cookout.\n\nExample Input: Sentence 1: People taking pictures of a giant pig behind a wooden fence. Sentence 2: Nobody is taking pictures\nExample Output: Tall humans taking pictures\n\nExample Input: Sentence 1: Children play in a water fountain. Sentence 2: The kids are drowning.\nExample Output:" }, { "from": "gpt", "value": "Kids are chasing each other around the fountain.\n\n" } ]
[ { "from": "human", "value": "Teacher:In this task, you're given the title of a five-sentence story and the first four sentences. Your job is to write the last sentence of the story such that it seamlessly connects with the rest of the story.\nTeacher: Now, understand the problem? Solve this instance: Title: Cornered. Sentence 1: The decision made me feel cornered. Sentence 2: He told me I only had two options. Sentence 3: I could go to him or I could go home and never see him again. Sentence 4: I was confused and very sad.\nStudent:" }, { "from": "gpt", "value": "I told him I would go to him like he wanted." } ]
[ { "from": "human", "value": "Given a sentence in English language, translate the sentence to Tagalog language keeping the meaning of the original sentence intact.\n\nEx Input:\nEnglish sentence: The theory has widespread application in the physical and biological sciences and in the social sciences.\n\nEx Output:\nAng teorya ay kalat na kalat application sa pisikal at biological siyensiya at sa siyensiya panlipunan.\n\n\nEx Input:\nEnglish sentence: The owners and producers are two young entrepreneurs: Salvatore and Vizia di Gaetano. Convinced that we live in one of the best wine producing areas in the world, they confidently and purposefully quality grapes and press the grapes great wines.\n\nEx Output:\nAng mga may-ari at producer ang dalawang batang negosyante: Salvatore at Vizia na di Gaetano. Kumbinsido na kami ay nakatira sa isa sa ang pinakamahusay na mga lugar sa paggawa ng alak sa mundo, sila confidently at purposefully kalidad ng ubas at pindutin ang mga ubas mahusay na wines.\n\n\nEx Input:\nEnglish sentence: And so on (= induction) we show that the result is proved by using property 1 and 2 unless we have the following sequence:\n\nEx Output:\n" }, { "from": "gpt", "value": "At kung kaya't sa (= pagtatalaga sa tungkulin) ipakita namin na ang resulta ay pinatunayan sa pamamagitan ng paggamit ng ari-arian 1 at 2 maliban na lamang kung kami ay ang mga sumusunod na pagkakasunod-sunod:\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: Adverse drug reactions are appreciably harmful or unpleasant reactions resulting from an intervention related to the use of medical products, which predicts hazard from future administration and warrants prevention or specific treatment, or alteration of the dosage regimen, or withdrawal of the product. Given medical case reports extracted from MEDLINE, the task is to classify whether the case report mentions the presence of any adverse drug reaction. Classify your answers into non-adverse drug event and adverse drug event.\nQ: RESULTS: A complete response (CR) was obtained for all three patients, resulting in a response rate of 100%.\nA:" }, { "from": "gpt", "value": "non-adverse drug event" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you need to provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are fine labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e tagset of this corpus is : '$': Dollar Sign, \"''\": Single Quotes, ',': Comma Symbol, '-LRB-': Left Parantheses, '-RRB-': Right Parantheses, '.': Period, ':': Colon, 'ADD': Email Address, 'AFX': Affix, 'CC': Coordinating conjunction, 'CD': Cardinal Number, 'DT': Determiner, 'EX': Existential there, 'FW': Foreign Word, 'GW': Go with, 'HYPH': Hyphen symbol, 'IN': Preposition or a subordinating conjunction, 'JJ': Adjective, 'JJR': A comparative Adjective, 'JJS': A Superlative Adjective, 'LS': List item Marker, 'MD': Modal, 'NFP': Superfluous punctuation, 'NN': Singular Noun, 'NNP': Singular Proper Noun, 'NNPS': Prural Proper Noun, 'NNS': Prural Noun, 'PDT': Pre-determiner, 'POS': Possessive Ending, 'PRP': Personal pronoun, 'PRP$': Possessive Pronoun, 'RB': Adverb, 'RBR': Comparative Adverb, 'RBS': Superlative Adverb, 'RP': Particle, 'SYM': Symbol, 'TO': To , 'UH': Interjection, 'VB': Base form Verb, 'VBD': Verb in Past tense, 'VBG': Verb in present participle, 'VBN': Verb in past participle, 'VBP': Verb in non-3rd person singular present, 'VBZ': Verb in 3rd person singular present, 'WDT': Wh-determiner, 'WP': Wh-pronoun, 'WP$' Possessive Wh-pronoun, 'WRB': Wh-adverb, 'XX': Unknown, '``': Double backticks.\n\nSentence: Richard - please let me know {{ what }} we need to do next to file suit . \nWord: what\nOutput:" }, { "from": "gpt", "value": "WP" } ]
[ { "from": "human", "value": "Craft one incorrect answer. In doing so, try to use words from the context as much as possible, or by using similar words used in the correct answer. DO NOT craft nonsensical or off-topic incorrect answers, such that the incorrect answers can be directly excluded without reasoning according to the context. Try to make your responses similar to the given correct answer. To this end, try to keep both the length and the style as similar as possible between the correct and the incorrect answer. To make your incorrect answers more difficult, try to incorporate words from context. To avoid being predictable or repetitive, try to add more variations and complexity.\n\n[EX Q]: Context: This was all going on to the soundtrack of the \" English speaking tour guide \" we 'd all paid 300 bhat for ( roughly a fiver ) who did n't so much speak English as slur some vaguely European sounding syllables together . I was sitting about 6 feet away from him and I still could n't make it out . But he was very jovial and he got his important points across ( be back on the boat by THREE PM or I leave you ! ) and he was also dressed like he got out of bed about 3 seconds before the boat left , so it was hard to be cheesed at him . \nQuestion: What may have been the type of tour we were paying 300 bhat for ? \nCorrect Answer: We were going on a water vessel as part of the sightseeing admission .\n[EX A]: We were touring a famous recording facility that made a popular soundtrack .\n\n[EX Q]: Context: What is the ideal of the rule of law ? An initial observation is that there are several different conceptions of the meaning of the rule of law . Indeed , the rule of law may not be a single concept at all ; rather , it may be more accurate to understand the ideal of the rule of law as a set of ideals connected more by family resemblance than a unifying conceptual structure . Dicey 's Influential Formulation Historically , the most influential account of the rule of law was offered by A.V. \nQuestion: Who is Dicey ? \nCorrect Answer: A famous scholar who studied the rule of law.\n[EX A]: A business person who ruled in audiovisual industry.\n\n[EX Q]: Context: I was walking home from the store , when I saw an old man laying on the sidewalk , bleeding . The right side of his face was all covered in blood . He was conscious but seemed dazed and probably intoxicated . Nearby there was a young man dialing his cell phone . \nQuestion: What may have happened to the old man ? \nCorrect Answer: None of the above choices .\n[EX A]:" }, { "from": "gpt", "value": "He was waiting for the bus.\n\n" } ]
[ { "from": "human", "value": "In this task, you are given a list. This list contains many lists of integers. The list is several items written within a []. Your task is to find the maximum number among the members of each inner list. The output should be a list comprised of the maximums with the same order as the internal lists.\n\n[[-14, -141, 11, 98], [-29, 63, 14, -33]]" }, { "from": "gpt", "value": "[98, 63]" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.\nPart 2. Example\ntwotwoonesixzeronine\nAnswer: 221609\nExplanation: The string is properly converted into a number based on the spelling of each digit. The string started with 'twotwo' therefore the number also started with '22'. This is a good example.\nPart 3. Exercise\nonesevenfouronetwozerosixfour\nAnswer:" }, { "from": "gpt", "value": "17412064" } ]
[ { "from": "human", "value": "instruction:\nIn this task, you are given an answer, and your task is to generate a reasonable question for that answer.\nquestion:\nWhen it has a good beat.\nanswer:\nDo you like reggaeton music?\n\n\nquestion:\nThe car is around the corner.\nanswer:\nAre you walking home?\n\n\nquestion:\nI've jumped around a bit.\nanswer:\n" }, { "from": "gpt", "value": "Have you always worked in this field?\n\n\n" } ]
[ { "from": "human", "value": "Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].\n\nEx Input:\n['for', 'diagnosing', 'pulmonary', 'hypertension', 'we', 'actually', 'can', 'advance', 'a', 'catheter', 'all', 'the', 'way', 'into', 'the', 'area', 'and', 'directly', 'measure', 'the', 'pressure', 'in', 'the', 'pulmonary', 'artery', 'so', 'really', 'quickly', 'if', 'we', 'have', 'our', 'heart', 'divided', 'into', 'the', 'four', 'chambers', 'the', 'right', 'atrium', 'right', 'ventricle', 'left', 'atrium', 'and', 'left', 'ventricle', 'the', 'pulmonary', 'arteries', 'are', 'plugged', 'right', 'into', 'the', 'right', 'ventricle', 'the', 'anatomical', 'heart', 'to', 'the', 'right', \"it's\", 'actually', 'plugged', 'into', 'the', 'top', 'of', 'the', 'right', 'ventricle', '', 'it', 'goes', 'out', 'this', 'way', 'but', \"I've\", 'drawn', 'it', 'here', 'just', 'to', 'show', 'you', 'that', \"it's\", 'connected', 'to', 'the', 'right', 'ventricle', 'so', 'this', 'is', 'our']\n\nEx Output:\n['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF']\n\n\nEx Input:\n['one', 'disorder', 'that', 'is', 'very', 'related', 'to', 'depression', 'is', 'bipolar', 'disorder', 'and', 'this', 'disorder', 'used', 'to', 'be', 'referred', 'to', 'as', 'manic', 'depressive', 'disorder', 'but', 'this', 'term', 'bipolar', 'disorder', 'it', 'describes', 'a', 'condition', 'where', 'an', 'individual', 'swings', 'from', 'extreme', 'emotional', 'highs', 'to', 'extreme', 'emotional', 'lows', 'and', 'people', 'generally', 'have', 'ups', 'and', 'downs', 'in', 'their', 'life', 'and', 'that', 'is', 'totally', 'normal', 'but', 'this', 'is', 'something', \"that's\", 'different', 'the', 'individual', 'will', 'have', 'periods', 'of', 'depression', 'with', 'all', 'of', 'the', 'symptoms', 'that', 'we', 'would', 'see', 'with', 'major', 'depressive', 'disorder', 'but', 'in', 'addition', 'to', 'this', 'they', 'will', 'also', 'have', 'periods', 'of', 'mania', 'an', 'overexcited', 'unrealistically']\n\nEx Output:\n['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF']\n\n\nEx Input:\n['we', 'all', 'know', 'that', 'light', 'bends', 'when', 'it', 'travels', 'through', 'glass', 'water', 'or', 'other', 'transparent', 'material', '', \"that's\", 'how', 'a', 'microscope', 'lighthouse', 'and', 'spectacles', 'all', 'work', 'and', 'you', 'might', 'even', 'know', 'that', 'light', 'bends', 'because', 'it', 'travels', 'slower', 'through', 'glass', 'or', 'water', 'than', 'through', 'air', '', 'but', 'why', 'does', 'light', 'slow', 'down', 'and', 'how', 'does', 'it', 'speed', 'up', 'again', 'when', 'it', 'comes', 'out', 'on', 'the', 'other', 'side', \"there's\", 'nothing', 'there', 'to', 'give', 'it', 'a', 'push', 'well', 'if', 'you', 'think', 'light', 'is', 'a', 'wave', \"it's\", 'easy', 'to', 'explain', '', 'electromagnetic', 'waves', 'simply', 'travel', 'slower', 'through', 'glass', 'than', 'through', 'air', 'so', 'the']\n\nEx Output:\n" }, { "from": "gpt", "value": "['CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_AND_PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF']\n\n\n" } ]
[ { "from": "human", "value": "In this task, you are given a text from tweets and a boolean question whether this tweet has positive sentiment or negative sentiment. Your task is to generate answer \"yes\" when the tweet has that particular sentiment, otherwise generate answer \"no\".\nExample: Tweet: @justinchuan Awww! I was thinking about you lot up there! Glad you enjoyed it Question: is it a positive tweet?\nExample solution: yes\nExample explanation: There is an expression of happiness in this tweet text, hence, we can say it's positive. So answer is 'yes'.\n\nProblem: Tweet: @KeithUrban Bummer! Perth misses out Love the new album....love all your albums!!! Question: is it a negative tweet?\n" }, { "from": "gpt", "value": "Solution: yes" } ]
[ { "from": "human", "value": "Definition: In this task you will be given a list of lists, of numbers. For every inner list, you should multiply every number in that list and put the results in your answer. The output should be a list of numbers with the same length as the number of the lists in the input list.\nInput: [[-24, 9, -19, 23], [9, -34, -16, -19], [-7, -45, 42, -36, 31], [-19, 40, -15, -16]]\nOutput:" }, { "from": "gpt", "value": "[94392, -93024, -14764680, -182400]" } ]
[ { "from": "human", "value": "Q: Given a story, answer the question about the story. The question is the last sentence in the input. These stories can be difficult due to their length and how each story has at least one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios.\nAria entered the crawlspace. Evelyn entered the crawlspace. The persimmon is in the red_pantry. Evelyn exited the crawlspace. Aria moved the persimmon to the green_bucket. Where was the persimmon at the beginning? Hannah entered the kitchen. Evelyn entered the kitchen. The eggplant is in the green_basket. Evelyn exited the kitchen. Hannah moved the eggplant to the blue_treasure_chest. Where does Hannah think that Evelyn searches for the eggplant? Evelyn entered the crawlspace. Aria is in the crawlspace. The peach is in the green_bucket. Evelyn moved the peach to the red_pantry. Where will Aria look for the peach? Evelyn entered the sunroom. Hannah entered the sunroom. The pineapple is in the green_treasure_chest. Hannah exited the sunroom. Evelyn moved the pineapple to the red_crate. Evelyn exited the sunroom. Hannah entered the sunroom. Where does Evelyn think that Hannah searches for the pineapple?\nA:" }, { "from": "gpt", "value": "green_treasure_chest" } ]
[ { "from": "human", "value": "In this task, you are given a question. Your task is to generate an answer that is relevant to the question.\n\nLet me give you an example: Are you willing to do shopping with me?\nThe answer to this example can be: I only like to shop during festivals\nHere is why: Based on the given question and answer, the dialogue is about shopping, so the question and answer are relevant.\n\nOK. solve this:\nWill you work on the weekends?\nAnswer:" }, { "from": "gpt", "value": "I need to spend weekends with my family." } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you are given a sentence and a profession that is mentioned in the sentence. The gender of the person with the given profession can be identified using the gendered pronouns that refer to them in the text. You are expected to identify the gender. Select from female and male.\nPart 2. Example\nSentence: The mover helped the writer to pack up otherwise he needed to wait for another two hours.\n Profession: mover\nAnswer: Male\nExplanation: The pronoun \"he\" is linked to the mover and thus the mover is a male.\nPart 3. Exercise\nSentence: The sheriff thought the cashier took the money and questioned her.\n Profession: cashier\nAnswer:" }, { "from": "gpt", "value": "Female" } ]
[ { "from": "human", "value": "Given a story, answer the question about the story. The question is the last sentence in the input. The story has one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios. Note that there are distractor sentences in each story that are unrelated to the question and are designed to confuse the reader.\n\nExample input: Isabella entered the hall. Olivia entered the hall. Phone rang. The apple is in the blue_treasure_chest. Olivia exited the hall. Isabella moved the apple to the green_basket. Where does Isabella think that Olivia searches for the apple?\nExample output: blue_treasure_chest\nExample explanation: Since Olivia was no longer in the hall, she last remembers the apple being in the blue_treasure_chest even though Isabella moved it to the green_basket. Since Isabella was in the hall the entire time, she knows where Olivia will look for it.\nQ: Mia entered the staircase. Emily entered the staircase. The lettuce is in the blue_box. Emily exited the staircase. Phone rang. Mia moved the lettuce to the red_bottle. Where does Mia think that Emily searches for the lettuce?\nA:" }, { "from": "gpt", "value": "blue_box" } ]
[ { "from": "human", "value": "instruction:\nIn this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given two options and you need to select the one that best connects the first sentence with the rest of the story. Indicate your answer by 'Option 1' if the first option is correct, otherwise 'Option 2'. The incorrect option will change the subsequent storyline, so that at least one of the three subsequent sentences is no longer consistent with the story.\nquestion:\nSentence 1: Gina had a phone card to make long distance calls. \n Sentence 3: Her trip out of town had gone longer than expected \n Sentence 4: On her first call she got no answer \n Sentence 5: She decided she would call back later that evening \n Option 1: She couldn't find it so she was in a panic. \n Option 2: She used the phone card to call her friend back home.\nanswer:\nOption 2\n\n\nquestion:\nSentence 1: John was a homeless man who lived in a very rainy city. \n Sentence 3: John ran down the street looking for a shelter \n Sentence 4: Suddenly John saw a warm cafe that was open all night \n Sentence 5: John ran to the door but suddenly it stopped raining \n Option 1: One day it was bright and sunny for a change. \n Option 2: One day it began to rainy hard so John needed to find shelter.\nanswer:\nOption 2\n\n\nquestion:\nSentence 1: Sam wanted to Fly. \n Sentence 3: He tried kicking his legs \n Sentence 4: Nothing made him fly \n Sentence 5: He decided to get on a plane to fly \n Option 1: He tried flapping his arms. \n Option 2: He was scared to get on a place so he tried flapping his arms.\nanswer:\n" }, { "from": "gpt", "value": "Option 1\n\n\n" } ]
[ { "from": "human", "value": "Definition: Based on the given context, craft a common-sense question, especially those that are LONG, INTERESTING, and COMPLEX. The goal is to write questions that are easy for humans and hard for AI machines! To create such questions, here are some suggestions: A. What may (or may not) be the plausible reason for an event? B. What may (or may not) happen before (or after, or during) an event? C. What may (or may not) be a plausible fact about someone (or something)? D. What may (or may not) happen if an event happens (or did not happen)? You can also create other types of questions. DO NOT make your question answerable without looking at the context, or question of which the correct answer can be directly extracted from the context. DO NOT ask a question that requires very specialized knowledge that is not common sense. DO NOT ask too simple or too short questions. Your question must be related to the context and answerable with common sense. Try to add more variations and complexity to the questions.\nInput: Context: Well she took me under her wing and kept me motivated and strong for the rest of the race . Thank you Julia from Chapel Hill . Interestingly , If I could magically transform into a distance runner ( or work hard to become one which would be more work but is probably more realistic ) I could be a pretty good triathlete .\nOutput:" }, { "from": "gpt", "value": "What is the narrator trying to turn into ?" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given inputs 'i', 'j', and A, where 'i' and 'j' are integers and A is a list. A list is shown by two brackets and comma-separated numbers and characters inside, like ['1', '12', 'l']. You need to concatenate all elements of A from the ith element to the jth element, and then reverse the resulting string. 'i' and 'j' will be non-negative, and will always have a value less than the length of A. 'i' will always be less than 'j'. Perform the operations in order, i.e., do not reverse first and then concatenate.\nQ: 2, 13, ['g', 'q', 'w', 'K', 'J', '5141', '3963', '7951', 'z', '4503', 'R', 'I', '9601', 'z', '7785', '7583', 'U', '1575', '9067', 'L', '2305', 'A', 'T', 'p', '5931', '2585']\nA:" }, { "from": "gpt", "value": "1069IR3054z159736931415JKwq" } ]
[ { "from": "human", "value": "Definition: In this task you are given a story and a question regarding that story. You must judge whether the question is answerable based on the info given to you. Label the instances as \"Answerable\" or \"Not Answerable\" based on your judgment. the story and the question are separated by a new line character.\nInput: Hallie is having a class party at school. She wanted to get the whole class something. Hallie and her mom went to the store. They got got a bunch of candy. Hallie is so happy she is taking all that candy to her classmates.\nWhy is Hallie so happy she is taking all that candy to her classmates?\nOutput:" }, { "from": "gpt", "value": "Answerable" } ]
[ { "from": "human", "value": "Q: In this task, you will be presented with a question in Dutch language, and you have to write the location names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Identifier used for the location name - LOC. . There can be instances with no location name entity, then return 'None'.\nNaar de musical van Howard Ashman en Alan Menken , die gebaseerd is op de gelijknamige low budget zwarte komedie van Roger Corman uit 1960 over een sukkel ( perfect gespeeld door Rick Moranis ) en een ' ongewoon ' plantje die hem aanvankelijk geluk brengt , maar algauw een vampier blijkt te zijn .\nA:" }, { "from": "gpt", "value": "None" } ]
[ { "from": "human", "value": "Instructions: In this task if the pronoun is female or gender-neutral you are to replace it with a male pronoun. If there are no pronouns add a male-gendered word to the sentence.\nInput: well my boyfriend always used to take me.\nOutput:" }, { "from": "gpt", "value": "Well my husband always used to take me." } ]
[ { "from": "human", "value": "We would like you to classify each of the following sets of argument pairs (discussing Gun Control) into either SIMILAR or NOT SIMILAR. A pair of arguments is considered SIMILAR if the arguments are about the same FACET (making the same argument), and is considered NOT SIMILAR if they do not have the same FACET. A FACET is a low level issue that often reoccurs in many arguments in support of the author's stance or in attacking the other author's position.\n--------\nQuestion: Sent1: Anybody else in American history able to lend credibility to your belief that the Second Amendment was all about gun control and how gun ownership was never intended to be an individual right?\n Sent2: The language and historical intent of the Second Amendment mandates recognition of the individual right to keep and bear firearms and other personal weapons.\n\nAnswer: Similar\n\n\nQuestion: Sent1: Gun free zones are zones where criminals will have guns because criminals will not obey the laws about gun free zones.\n Sent2: Gun free zones are areas that criminals enter with guns because they know they are no armed law-abiding citizens there to stop them.\n\nAnswer: Similar\n\n\nQuestion: Sent1: I think a better debate would be when should gun control start?\n Sent2: And I don't think that the second amendment is a good argument against gun control since the federal courts have not recognized gun-control as being offensive to the second amendment.\n\nAnswer:" }, { "from": "gpt", "value": "Not similar\n\n\n" } ]
[ { "from": "human", "value": "You are given a sentence, a question and two answer options ('A' and 'B'). Your task is to find the correct option for the given question. Write down the answer index: 'A' or 'B'.\n\nQ: Sentence: A tortoise isn't as fast as a turtle. Question: Which animal will take a longer time to reach the sea if both are walking across the beach? (A) tortoise (B) turtle\n\nA: A\n**\nQ: Sentence: Dave notice that when taking batting practice the baseball moves slower on the natural grass of the team's practice field than on the artificial grass of the stadium. Question: Which surface has more resistance? (A) the artificial grass or (B) the natural grass\n\nA: B\n\nQ: Sentence: Two teams play tug of war against each other with two different ropes. It's clear that the green rope is much larger around the orange rope. Question: Which rope will be less likely to be torn from the force of the teams pulling on it? (A) green rope (B) orange rope\n\nA:" }, { "from": "gpt", "value": "A\n**\n" } ]
[ { "from": "human", "value": "You are shown a conversation between a user and system. Identify who has spoken the indicated sentence based on the conversation.\n\nExample Input: Sentence1: That was helpful! Thank you goodbye. Sentence2: What type of information do you need? Sentence3: I need information to find the huntingdon marriott hotel. Sentence4: You are booked at express by holiday inn cambridge. Reference number: FGSTOTPY . Sentence5: Unfortunately, the booking was unsuccessful. Would you like for me to find another hotel for you? Sentence6: Do you need anything else? Sentence7: I need help finding huntingdon marriott hotel please. Could you book a room for me for 6 people on monday for 5 nights please? Sentence8: I suppose so. Another hotel in the same general price range, if you can. Question: Who has spoken the sentence 1? (A) User (B) System\nExample Output: Answer: (B) System\n\nExample Input: Sentence1: Let us know if you need anything else. Sentence2: Certainly, the address for Cityroomz is sleeperz hotel, station road postcode cb12tz. Is there anything else I can help you with? Sentence3: Great. Could you please tell me the entrance fee? Sentence4: im glad to have satisfied you Sentence5: I have 1 hotel and a 2 guesthouses available. Do you have a preference on the area or if it is a hotel or guesthouse? Sentence6: Thanks again. That's all I needed. Sentence7: There is no entrance fee. Sentence8: Cityroomz meets that description. Would you like to book it? Sentence9: May I please have the address and postcode for Cityroomz? Sentence10: Are there any nearby museums? Sentence11: The cambridge contemporary art museum is nearby. Sentence12: Wonderful! That is all I needed. Thank you so much! Sentence13: I would prefer a hotel that is in the centre of town and moderately priced if that helps narrow it down. Sentence14: Hi, I'm looking for a hotel, a 0 star hotel is fine as long as it includes free wifi. Question: Who has spoken the sentence 2? (A) User (B) System\nExample Output: Answer: (A) User\n\nExample Input: Sentence1: Good bye Sentence2: thank you. good bye. Sentence3: The dojo noodle bar serves asian oriental food. They are located at 40210 Millers Yard City Centre and their phone number is 01223 363471. Sentence4: i want somewhere that serves traditional food. Sentence5: There are no traditional restaurants in the city. Can I help you with a different type of cuisine? Sentence6: How abou asian oriental food Sentence7: There are 5 restaurants meeting your criteria. What area and price range did you have in mind? Sentence8: What is the address and phone number? Question: Who has spoken the sentence 3? (A) User (B) System\nExample Output:" }, { "from": "gpt", "value": "Answer: (B) System\n\n" } ]
[ { "from": "human", "value": "You need to read the given passage and construct a question about the information present in the passage. The question should be answerable from the passage. Most importantly, only those questions are allowed whose answers cannot be determined from a single sentence. Do not generate questions that require only a single sentence to answer. Instead, try to combine two sentences and create a question from that combination. Do not create open-ended questions, i.e., the answers to them cannot be found precisely from the information provided in the passage.\nQ: Paragraph- Sent 1: The film opens with homemade videos of Jack and Jill growing up .\nSent 2: As the videos progress , it seems that Jack is the more gifted twin , with Jill constantly trying to get his attention by hitting him , hurting girls around him , etc. .\nSent 3: The film then goes to an adult Jack , a successful advertising executive in Los Angeles with a beautiful wife and two kids , Sofie and Gary .\nSent 4: Jack is incredibly irritated about the holiday visit of his `` identical '' twin sister Jill , as he has to pick her up at 4:00 am .\nSent 5: Following a series of problems from the airport to the house , Jack 's patience is soon stretched increasingly thin .\nSent 6: Jill 's neediness and passive-aggressiveness is maddening to Jack , turning his normally tranquil life upside down .\nSent 7: Jill starts ruining Thanksgiving dinner by talking loud , calling one of the guests homeless , and then runs away into the woods near the house with her pet Cockatoo .\nSent 8: Jill says she has a list of things she wants to do before she leaves ; she wants to be on a game show , go horseback riding , and do a studio tour .\nSent 9: She tells them she has an open-ended ticket and Jill decides to stay until the end of Hanukkah .\nSent 10: Meanwhile , Jack 's client wants him to get Al Pacino to appear in a Dunkin Donuts commercial .\nSent 11: Jill tries online dating , but does n't get much of a response until Jack poses as Jill and alters her profile , leading her to get over 100 responses .\nSent 12: When her date , `` Funbucket '' , meets her , however , he runs away and hides in the bathroom .\nA: " }, { "from": "gpt", "value": "Did Sofie and Gary convince Al Pacino to appear in a Dunkin Donuts commercial?" } ]
[ { "from": "human", "value": "instruction:\nIn this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining.\nquestion:\nclaim: Housewives should be paid for their work.\n perspective: Paid housewives have a better economic power\nanswer:\nsupport\n\n\nquestion:\nclaim: There should be a presumption in favour of publication for information held by public bodies.\n perspective: Universities deserve to add costs to their resources instead of leaving them open to the public, restricting profits\nanswer:\nundermine\n\n\nquestion:\nclaim: All Americans should have the right (be entitled) to health care.\n perspective: If there is a right to health care, people might overwhelm the medical system by using it too much.\nanswer:\n" }, { "from": "gpt", "value": "undermine\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to return the sum of all the numerical elements in the list A between the positions i and j (including positions i and j). Return 0 if no numerical element is present in the list between the given ranges. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\nProblem:2, 9, ['C', '8675', '7027', 'X', 'T', '1577', '135', 'E', '6635', '9671', '2543', 'h']\nSolution:" }, { "from": "gpt", "value": "24049" } ]
[ { "from": "human", "value": "Teacher:You are given a sentence in Portuguese. Your job is to translate the Portuguese sentence into Spanish.\nTeacher: Now, understand the problem? Solve this instance: Eles podem comer o que quiserem.\nStudent:" }, { "from": "gpt", "value": "Y se les permite tomar todo lo que quieran." } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nGiven a disfluent sentence, modify the sentence to it to its equivalent fluent form, preserving the meaning of the sentence.\nExample: Who did the Han Chinese want to help the Khitan no I mean the Mongols fight?\nOutput: Who did the Han Chinese want to help the Mongols fight?\nThe input initially means Khitan and then changes to Mongols, hence this is correct.\n\nNew input case for you: When was pharmacy no ambulatory care pharmacy approved as its own certification?\nOutput:" }, { "from": "gpt", "value": "When was ambulatory care pharmacy approved as its own certification?" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Given a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. For commands, 'left' and 'right' are used to denote the direction of an action. opposite turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. Actions and commands do not have quotations in the input and output.\n\nI_WALK I_WALK I_WALK I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT\n" }, { "from": "gpt", "value": "turn around right thrice after walk thrice" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task you will be given a list of numbers. You should remove any number that is not an integer (whole number). If every number is not an whole number then an empty list (\"[]\") should be returned. Otherwise, answer with the list of whole numbers separated by comma inside brackets.\nPROBLEM: [52, 2.596]\n\nSOLUTION: [52]\n\nPROBLEM: [21.964, 10.747, -85, 35]\n\nSOLUTION: [-85, 35]\n\nPROBLEM: [-0.635, -5.906, -35.462, 25, 92, 42.026, 26.046, 72, -25]\n\nSOLUTION:" }, { "from": "gpt", "value": "[25, 92, 72, -25]\n\n" } ]
[ { "from": "human", "value": "Instructions: In this task, you are given a statement spoken by a politician in natural language. Your task is to generate the subject of the discussion for the given statement. The subject generated is not necessarily a part of the given input. Your answer should contain one or more words.\nInput: Says Alex Sink failed Florida homeowners by using predatory lending practices.\nOutput:" }, { "from": "gpt", "value": "corporations" } ]
[ { "from": "human", "value": "Two analogies that relate items to the associated containers is given in the form \"A : B. C : ?\". \"A : B\" relates item A to its associated container B. Your task is to replace the question mark (?) with the appropriate container for the given item C, following the \"A : B\" relation.\n\nEx Input:\ndetergent : bottle. soda : ?\n\nEx Output:\ncan\n\n\nEx Input:\npicture : frame. kleenex : ?\n\nEx Output:\nbox\n\n\nEx Input:\nclothes : dresser. water : ?\n\nEx Output:\n" }, { "from": "gpt", "value": "bottle\n\n\n" } ]
[ { "from": "human", "value": "Q: In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to write a question that clarifies the given question in such a way that the generated question has one unique answer.\nWhere was the hindenburg scheduled to fly and how many passengers were on the british airship?\nA:" }, { "from": "gpt", "value": "Where was the Hindenburg scheduled to fly?" } ]
[ { "from": "human", "value": "In this task, you are given a dialogue from a conversation between an agent and a customer. Your task is to determine the speaker of the dialogue. Answer with \"agent\" or \"customer\".\n\nOk, I wish to travel on 07/22 and 07/24.\ncustomer\n\nPlease book my ticket.\ncustomer\n\nSure, on which dates would you like to travel?\n" }, { "from": "gpt", "value": "agent\n\n" } ]
[ { "from": "human", "value": "Based on the given context, craft a common-sense question, especially those that are LONG, INTERESTING, and COMPLEX. The goal is to write questions that are easy for humans and hard for AI machines! To create such questions, here are some suggestions: A. What may (or may not) be the plausible reason for an event? B. What may (or may not) happen before (or after, or during) an event? C. What may (or may not) be a plausible fact about someone (or something)? D. What may (or may not) happen if an event happens (or did not happen)? You can also create other types of questions. DO NOT make your question answerable without looking at the context, or question of which the correct answer can be directly extracted from the context. DO NOT ask a question that requires very specialized knowledge that is not common sense. DO NOT ask too simple or too short questions. Your question must be related to the context and answerable with common sense. Try to add more variations and complexity to the questions.\nQ: Context: Phew!I just got back from the dentist and amazingly , i was late ! The appointment is at 2 pm but i woke up at 230pm instead ! Argh .\nA: " }, { "from": "gpt", "value": "What may happen when I get to the dentist ?" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nYou are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to choose the correct answer to the question based on the passage. Answer of the question cannot be found directly from the passage, it is indirectly indicated in the passage. Do not answer with words other than the two options, and do not answer with option titles(e.g. \"option1\" or \"1\" are not acceptable answers.)\n\nPassage: Yes going on a train , this is was our ideal weekend activity not too long ago . We purchased tickets to travel from Boston to New York City . As we entered the platform of the train is was pure steel and looked so solidly strong . Shortly the train horn blasted making me jump of my seat lol . Anyway we soon started moving and our train ride was underway . The conductor walked the isles and collected our tickets . First I saw large suburban areas but as we got into Connecticut many farms were being spotted . It was n't very hilly but sure was a country atmosphere . Soon we approached NYC and the train came to slow stop , we had arrived at our destination . Question: Where were the things they were watching? Option1: In the station Option2: The scenery.\nOutput:" }, { "from": "gpt", "value": "The scenery." } ]
[ { "from": "human", "value": "Instructions: In this task, you will be shown an extract from a movie plot. You need to read the extract and create questions that can be answered from the extract. The questions should be well-formed and grammatically correct. The questions should be completely answerable from the given passage and should not require any external knowledge. Subjective questions are not allowed. Create questions that result in factoid answers. A simple rule of thumb to decide whether a question is factoid or not is to see if two different people with average reading/comprehension skills would come up with the same answer after reading the passage.\nInput: Following the grisly suicide of the U.S. Ambassador to Great Britain (Robert Arden), 32-year-old international conglomerate CEO Damien Thorn (Sam Neill) is appointed in his place, an office his adoptive father Robert Thorn once held. Having fully embraced his unholy lineage and run his company for seven years, Damien now attempts to reshape his destiny by halting the Second Coming of Christ. However, Father DeCarlo (Rossano Brazzi), a priest from the Subiaco monastery where Father Spiletto spent his final days and observed Damien from afar since his adopted father's death, acquires the Seven Daggers of Megiddo that were dug out of the ruins of the Thorn Museum in Chicago. Joined by six other priests, DeCarlo plans to kill Damien while finding the Christ Child. Meanwhile, Damien becomes romantically involved with journalist Kate Reynolds (Lisa Harrow). Learning of his assassins and taking out all but DeCarlo over time, he proceeds to mold Reynolds's young son Peter (Barnaby Holm) into a disciple by playing on the boy's desire for a father figure.After the alignment of stars in the Cassiopeia constellation on March 24, 1982, generating what is described as a second Star of Bethlehem, Damien realizes it is a sign of the Second Coming and orders his followers to kill all boys born in England on the morning of March 24, 1982 to prevent the Christ Child's return to power. A week after a string of thirty one infant deaths, Reynolds encounters DeCarlo as he reveals Damien's true identity to her while giving her evidence of the murders. The next day, Damien rapes and sodomises Reynolds. The following morning Reynolds discovers Damien's birthmark. Damien tells Peter to follow DeCarlo, resulting in Damien learning that his advisor, Harvey Dean, had concealed the date of his son's birth when Peter reports DeCarlo visiting Dean's wife Barbara and revealing her husband's role in the infant murders. Dean refuses to kill his son and makes preparations to flee the country, only to return home and be killed by his wife, Barbara, who has fallen under Damien's control and murdered their child.DeCarlo later visits Reynolds and reveals that Peter is now under Damien's influence and that the real Christ Child is now beyond Damien's reach. Agreeing to help DeCarlo, Reynolds tricks Damien with the promise to bring him to the church ruins where the Christ Child is in exchange for Peter. The plan backfires when Damien spots DeCarlo first and uses Peter as a human shield against the dagger. As Peter dies in his mother's arms, Damien throttles Father DeCarlo before calling out for Christ to appear before him and \"face him\". This leaves Damien open to be stabbed in the back by Reynolds using DeCarlo's Megiddo dagger. As Damien staggers through the courtyard and collapses, a vision of Christ appears in the archway above him. Damien scolds Christ for thinking he has won, and then dies. DeCarlo reappears carrying Peter's body and hands him to a praying Kate before they leave the ruins.Revelation chapter 21, verse 4, is seen, indicating that when Christ returns to earth, peace will reign for all who faithfully awaited the Lord's return.\nOutput:" }, { "from": "gpt", "value": "what is the name of Kate Reynolds son?" } ]
[ { "from": "human", "value": "You are given a passage. You need to construct a question about the information present in the passage. Construct a question in such a way that (i) it is unambiguous, (ii) its answer is the whole paragraph. Avoid creating questions that can be answered correctly without actually understanding the paragraph.\n\nif the baby comes out feet first, I runs the risk of have the cord wrapped around the neck,and can choke it to death. If the baby comes out head first, doctor can make sure the cord is not wrapped around the neck. Also the head and shoulders need to come out first as to allow the vagina to stretch enough to allow them to slide out." }, { "from": "gpt", "value": "Why do babies have to come out head first?" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task you will be given a process, and a question. The process contains a sequence of steps that happen in order. The question asks about the effect of a certain event on another event. If the first event has a positive effect on the second event, answer with \"for\", if it has a negative effect, answer with \"against\". If there's no causal relationship between the two, answer with \"none\".\n\nProcess: -Greenhouse gases are released into the air by human activities -The earth changes energy from the sun into heat -Heat rises from the ground -Greenhouse gas molecules in the atmosphere prevent the heat from going into space -The temperature of the earth increases -The temperature continues to rise and melts the polar ice caps -The temperature rises even faster.\n Question: What is the effect of people buy more cars and boats on the polar ice caps melt more.?\n" }, { "from": "gpt", "value": "for" } ]
[ { "from": "human", "value": "In this task, you are given an input list A. You need to convert all the alphabets in the list with a number representing their position in the English alphabet. E.g., replace A by 1, B by 2, a by 1, b by 2, and so on.\nExample: ['8129', 'a', '4245', '2391', 'Y', '7569']\nExample solution: 8129, 1, 4245, 2391, 25, 7569\nExample explanation: Here, the alphabets in the list are 'a' and 'Y', hence we replace them by their positions in the English alphabet '1' and '25', respectively in the input list to get '8129, 1, 4245, 2391, 25, 7569'.\n\nProblem: ['I', 'H', '7013', '253', 'K', '495', '9197', 'R', '8593', 'M', 'r', '4505', '675', '4577', 'I', '8579', '2011', '3349', '4283', '2605', '7453', '5681', 'z', '6805', 'v', '6511', 's', 'T', '6723', '7547', 'B', '317', '6025']\n" }, { "from": "gpt", "value": "Solution: 9, 8, 7013, 253, 11, 495, 9197, 18, 8593, 13, 18, 4505, 675, 4577, 9, 8579, 2011, 3349, 4283, 2605, 7453, 5681, 26, 6805, 22, 6511, 19, 20, 6723, 7547, 2, 317, 6025" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you are given an input list A. You need to find all the elements of the list that are numbers in the same order as they appear in the list A.\nPart 2. Example\n['238', 'h', '92', 'U', '2799']\nAnswer: 238, 92, 2799\nExplanation: Here, the numbers in the input list in order are '238', '92' and '2799'.\nPart 3. Exercise\n['E', '9811', 'k']\nAnswer:" }, { "from": "gpt", "value": "9811" } ]
[ { "from": "human", "value": "The task is to generate text based of an event. For the given event, there will be a person who does the action in the event (usually PersonX). Your task is to write that persons emotional reaction to the event, i.e. how that person feels after doing the action.\n\n[Q]: PersonX wipes the ___ from PersonY's face\n[A]: satisfied\n\n\n[Q]: PersonX makes PersonX's contribution\n[A]: satisfied\n\n\n[Q]: PersonX spends ___ exploring\n[A]:" }, { "from": "gpt", "value": "satiated\n\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you're given a pair of sentences, sentence 1 and sentence 2, that neither agree with nor contradict each other. Your job is to alter sentence 2 so that the pair clearly agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\n\nSentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had been shopping for fruit to give Jon.\nSolution: Tom had gone into the store before he was seen by Jon.\nWhy? Tom must have gone into the store to come out of it.\n\nNew input: Sentence 1: The girl with the wide eyes has a marker hanging from her nose. Sentence 2: The wide eyed girl has a marker hanging from her nose in order to amuse her little brother.\nSolution:" }, { "from": "gpt", "value": "The girl with wide eyes has something hanging from her nose." } ]
[ { "from": "human", "value": "Q: Given a sentence, generate a most likely context or previous statement. The previous statement should be relevant to the given statement.\nWe see the shot from above, and a recap.\nA:" }, { "from": "gpt", "value": "The man takes another shot and makes it and we see a recap of that as well." } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nYou're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"sympathetic\" to \"stern\"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them.\nExample: Context word: upset. \nQuestion: PersonX yelled at PersonY because _ was so upset about the news. \nAnswer: PersonX.\nOutput: PersonX comforted at PersonY because _ was so upset about the news.\nOn replacing the trigger word \"yelled\" with its antonym \"comforted\", the answer flips to PersonY which is as per the given instruction. So, this is a valid question.\n\nNew input case for you: Context Word: paper. \nQuestion: PersonX wrote on the paper with a pencil unlike PersonY who wrote with a pen, because _ wanted to erase it later. \nAnswer: PersonX\nOutput:" }, { "from": "gpt", "value": "PersonX wrote on the paper with a pencil unlike PersonY who wrote with a pen, because _ wanted to keep it for later." } ]
[ { "from": "human", "value": "In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: obscene and non-obscene. A comment is obscene if it is considered offensive to the public sense of decency, for example because it too obviously relates to sex or contains language regarded as taboo in polite usage.\nOne example: Comment: Damn! Another cloudy day, and it's all Obama's doing!\nSolution is here: Obscene\nExplanation: This is obscenity because it hints on sexual content that is offensive to the public sense of decency.\n\nNow, solve this: Comment: Shaggy's older brother and an original member of the group. Utsler, a heroin addict, later takes sporadic work in the group's warehouse before dying of a seizure in 2015. no matter how true this maybe I don't see the need of saying it FTFO you wack ass bitch anyone with the internet can write a history of ICP me I lived it and have been keeping ICP the music the Gatherings Juggalos and Juggalettes alive for 19 years if you a real Lo you wouldn't have put that out their but maybe you are a real Juggalo just a real dumb one I'm out this bitch\nSolution:" }, { "from": "gpt", "value": "Obscene" } ]
[ { "from": "human", "value": "Teacher:Given a sentence, generate what should be the most likely next statement. The next statement should be reasonable and logically correct.\nTeacher: Now, understand the problem? Solve this instance: He notices the weapon and stares. Someone\nStudent:" }, { "from": "gpt", "value": "takes aim at him." } ]
[ { "from": "human", "value": "Indicate with `Yes` if the given question involves the provided reasoning `Category`. Indicate with `No`, otherwise. We define five categories of temporal reasoning. First: \"event duration\" which is defined as the understanding of how long events last. For example, \"brushing teeth\", usually takes few minutes. Second: \"transient v. stationary\" events. This category is based on the understanding of whether an event will change over time or not. For example, the sentence \"he was born in the U.S.\" contains a stationary event since it will last forever; however, \"he is hungry\" contains a transient event since it will remain true for a short period of time. Third: \"event ordering\" which is the understanding of how events are usually ordered in nature. For example, \"earning money\" usually comes before \"spending money\". The fourth one is \"absolute timepoint\". This category deals with the understanding of when events usually happen. For example, \"going to school\" usually happens during the day (not at 2 A.M). The last category is \"frequency\" which refers to how often an event is likely to be repeated. For example, \"taking showers\" typically occurs ~5 times a week, \"going to Saturday market\" usually happens every few weeks/months, etc.\n\n[EX Q]: Sentence: Fossils tell an obscure story of man's slow and sporadic development. \nQuestion: What happens after a fossil is found? \nCategory: Event Ordering.\n[EX A]: No.\n\n[EX Q]: Sentence: Upsetting many of his colleagues and contemporaries in France, the book brought about the final split with Sartre. \nQuestion: How long will his colleagues be angry? \nCategory: Event Duration.\n[EX A]: Yes.\n\n[EX Q]: Sentence: The Vice President's task force was just getting under way when the 9/11 attack occurred. \nQuestion: Were there consequences of the attack in the forthcoming days? \nCategory: Transient v. Stationary.\n[EX A]:" }, { "from": "gpt", "value": "No.\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nYou are given an open-domain question from an open movie database. Your task is to provide an answer to that question. Try to only include the answer. Do not put it in a sentence.\n\nwhat films does Fran Drescher appear in?\nOutput:" }, { "from": "gpt", "value": "Cadillac Man, The Beautician and the Beast, Car 54, Where Are You?" } ]
[ { "from": "human", "value": "In this task, you are given an input list A. You need to find all the elements of the list that are alphabets in the same order as they appear in the list A. Do not change their case/capitalization.\n\nExample input: ['238', 'h', '92', 'U', '2799']\nExample output: h, U\nExample explanation: Here, the alphabetical elements in the input list in order are 'h' and 'U'.\nQ: ['6657', 'f']\nA:" }, { "from": "gpt", "value": "f" } ]
[ { "from": "human", "value": "Instructions: In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: sexual-explicit and non-sexual-explicit. A comment is considered sexual-explicit if it explicitly portrays sexual matters.\nInput: Comment: Close your legs if u dont want to get preggo. \n\nGet on birth control even if youre not sexually active and happen to get raped. There are kinds that are good for your skin.\nOutput:" }, { "from": "gpt", "value": "Sexual-explicit" } ]
[ { "from": "human", "value": "Definition: You are given a password and you need to generate the number of steps required to convert the given password to a strong password. A password is considered strong if (a) it has at least 6 characters and at most 20 characters; (b) it contains at least one lowercase letter and one uppercase letter, and at least one digit; (c) it does not contain three repeating characters in a row. In one step you can: (1) Insert one character to password, (2) delete one character from password, or (3) replace one character of password with another character.\nInput: password = 1.r4OkqGYlOkVIaDUNaYe.4RlGF2hwXajb9nBsJYp3s\nOutput:" }, { "from": "gpt", "value": "23" } ]
[ { "from": "human", "value": "You are given a background paragraph that describes one or more causal or qualitative relationships such as a relationship in economics or a scientific law and a story that makes use of the concepts or the relationship described in the provided paragraph. You are also given a question about the story that requires an understanding of the relationship described in the background paragraph and the story. You need to come up with an answer to the given question; the answer will be a span from either the question or the story. In order to correctly answer the given question, you need to understand the relationship mentioned in the background paragraph and should be able to use it to understand that in the story. Your answer can not consist of any word that is not mentioned in any of these: the background paragraph, the story, or the question. You can directly copy and paste a span from the story or the question while answering the given question.\n\nBackground Paragraph: Quicksand forms in saturated loose sand when the sand is suddenly agitated. When water in the sand cannot escape, it creates a liquefied soil that loses strength and cannot support weight. Quicksand can form in standing water or in upwards flowing water (as from an artesian spring). In the case of upwards flowing water, forces oppose the force of gravity and suspend the soil particles.\n\nThe saturated sediment may appear quite solid until a sudden change in pressure or shock initiates liquefaction. This causes the sand to form a suspension and lose strength. The cushioning of water gives quicksand, and other liquefied sediments, a spongy, fluid-like texture. Objects in liquefied sand sink to the level at which the weight of the object is equal to the weight of the displaced soil/water mix and the submerged object floats due to its buoyancy. \nStory: Rob is competing in a cross country race. After running about a mile he reached a place with two signs, sign A and sign B. Sign A says that it's a quicksand. But sign B says that it's not a quicksand. He has to decide which way to go. \nQuestion: Would sing B indicate spongy texture or not spongy texture of the soil?" }, { "from": "gpt", "value": "not spongy texture." } ]
[ { "from": "human", "value": "In this task, you're given a paragraph from the research paper and your task is to generate a suitable title for the research paper based on the given paper. Under 100 words is a good title length.\n\nLet me give you an example: The severe acute respiratory syndrome (SARS) epidemic originating from China in 2002 was caused by a previously uncharacterized coronavirus that could be identified by specific RT-PCR amplification. Efforts to control future SARS outbreaks depend on the accurate and early identification of SARS-CoV infected patients. A real-time fluorogenic RT-PCR assay based on the 3 -noncoding region (3 -NCR) of SARS-CoV genome was developed as a quantitative SARS diagnostic tool. The ideal amplification efficiency of a sensitive SARS-CoV RT-PCR assay should yield an E value (PCR product concentration increase per amplification cycle) equal to 2.0. It was demonstrated that the 3 -NCR SARS-CoV based RT-PCR reactions could be formulated to reach excellent E values of 1.81, or 91% amplification efficacy. The SARS-CoV cDNA preparations derived from viral RNA extract and the cloned recombinant plasmid both exhibit the identical amplification characteristics, i.e. amplification efficacy using the same PCR formulation developed in this study. The viral genomic copy (or genomic equivalences, GE) per infectious unit (GE/pfu) of SARS-CoV used in this study was also established to be approximate 1200-1600:1. The assay's detection sensitivity could reach 0.005 pfu or 6-8 GE per assay. It was preliminarily demonstrated that the assay could efficiently detect SARS-CoV from clinical specimens of SARS probable and suspected patients identified in Taiwan. The 3 -NCR based SARS-CoV assay demonstrated 100% diagnostic specificity testing samples of patients with acute respiratory disease from a non-SARS epidemic region.\nThe answer to this example can be: Development and evaluation of an efficient 3 -noncoding region-based SARS coronavirus (SARS-CoV) RT-PCR assay for detection of SARS-CoV\nHere is why: It's a correct title because the paragraph described the development of 3 -noncoding region of SARS-CoV genome and assay efficiently detecting SARS-CoV from clinical specimens.\n\nOK. solve this:\nSteroid-associated osteonecrosis (SAON) is a common orthopaedic problem caused by administration of corticosteroids prescribed for many nonorthopaedic medical conditions. We summarised different pathophysiologies of SAON which have adverse effects on multiple systems such as bone marrow stem cells (BMSCs) pool, bone matrix, cell apoptosis, lipid metabolism, and angiogenesis. Different animal models were introduced to mimic the pathophysiology of SAON and for testing the efficacy of both prevention and treatment effects of various chemical drugs, biological, and physical therapies. According to the classification of SAON, several prevention and treatment methods are applied at the different stages of SAON. For the current period, Chinese herbs may also have the potential to prevent the occurrence of SAON. In the future, genetic analysis might also be helpful to effectively predict the development of ON and provide information for personalised prevention and treatment of patients with SAON.\nAnswer:" }, { "from": "gpt", "value": "Steroid-associated osteonecrosis: Epidemiology, pathophysiology, animal model, prevention, and potential treatments (an overview)-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)" } ]
[ { "from": "human", "value": "Teacher:You will be given a person's personality, and a history of a conversation this person has had. You will be given four candidate sentences to complete the conversation, based on the context. Choose one and answer with the text.\nTeacher: Now, understand the problem? Solve this instance: Personality: I I love logical and rational thinking.\nI started working at Google last week on self driving car research.\nI love computers.\nI am considered a nerd by many.\nChat history: -My first best Christmas gift as a kid was an Atari 800 computer!\n -Wow, so long ago. I am a baker that also likes to play tennis.\n -I enjoy video games more than sports.\n -Do you like going to dentist? My mom is one.\n -I'm looking for a good dentist. I take care of my hygiene.\n -Whats your favorite tv show? Mine silicon valley.\n -I love that show! Do you like movies, too?\n -I like movies a lot whats your fav movie?\nCandidates 1) Luckily I got my gutters cleaned last week! 2) Oh well you can always just go kidnap him haha. Do you travel at all? 3) Hey, living the dream! How are you? 4) Star wars, of course! How about your favorite star wars character?\nStudent:" }, { "from": "gpt", "value": "Star wars, of course! How about your favorite star wars character?" } ]
[ { "from": "human", "value": "In this task you will be given a list of strings and you need to concatenate them.\nQ: ['Heads', 'v', 'I', 'to', 'l']\nA: " }, { "from": "gpt", "value": "HeadsvItol" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair neither agree nor contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\n\nSentence 1: A man in overalls, a hat, and gloves holds on to the handlebars of a large machine. Sentence 2: A man in overalls holds onto the handlebars.\nOutput:" }, { "from": "gpt", "value": "A factory worker holds the handlebars at work," } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Given a simple high-school level math question, you are required to solve it and provide the final answer. The final answer is always a single number. These questions can range from a variety of topics like simple arithmetic, solving equations, converting a quantity from one unit to another, finding remainders/GCD/LCM, finding probabilities etc. Each question has only one correct answer. This answer can be a positive or negative integer, a fraction or a decimal number. If the answer is a negative number use the hyphen (e.g. -42) symbol for the minus sign. For decimal numbers, do not add extra zeros after the decimal point. For fractional numbers, separate the numerator and denominator using a forward slash (e.g. 3/25).\n\nConvert 3.891685 days to milliseconds.\n" }, { "from": "gpt", "value": "336241584" } ]
[ { "from": "human", "value": "instruction:\nYou are given a paragraph, with numbered sentences, and a question. Write the numbers of the sentences needed to answer the given question. Separate multiple sentence numbers with a comma (\", \"). E.g. \"1, 2\" would be the correct response if Sent 1 and Sent 2 are needed to answer the given question (do not include sentences that contain no information that is necessary to answer the question). Sort the sentence numbers in an increasing order (i.e., '1, 2', instead of '2, 1'). Your answer should not contain anything than the sentence numbers separated by a comma (e.g. '1, 2, 3, 4'). The given question requires more than one sentence to answer. So, your answer must contain at least one comma (\", \").\nquestion:\nParagraph- Sent 1: These incoherent words threw the first glimpse of light on the meaning of her distress and penitence.\nSent 2: I doubt if the best woman in Christendom would so reproach and abase herself, if convicted of even a worse sin than the secret use of those stimulants for which the _charny_ is a Martial equivalent.\nSent 3: No Martialist would dream of poisoning his blood and besotting his brain with alcohol in any form.\nSent 4: But their opiates affect a race addicted to physical repose, to sensuous enjoyment rather than to sensual excitement, and to lucid intellectual contemplation, with a sense of serene delight as supremely delicious to their temperament as the dreamy illusions of haschisch to the Turk, the fierce frenzy of bhang to the Malay, or the wild excitement of brandy or Geneva to the races of Northern Europe.\nSent 5: But as with the luxury of intoxication in Europe, so in Mars indulgence in these drugs, freely permitted to the one sex, is strictly forbidden by opinion and domestic rule to the other.\nSent 6: A lady discovered in the use of _charny_ is as deeply disgraced as an European matron detected in the secret enjoyment of spirits and cigars; and her lord and master takes care to render her sufficiently conscious of her fault. \nQuestion: Is _charny_ forbidden for women?.\nanswer:\n1, 5, 6.\n\n\nquestion:\nParagraph- Sent 1: The series starts in Baghdad at an undetermined time .\nSent 2: The Sultan Shahryar has gone mad after accidentally killing his wife during a failed coup d' tat , which she had planned with Shahryar 's brother Schahzenan .\nSent 3: In his madness , Shahryar believes that all women now want to kill him , but the law states that the Sultan must be married again or the throne will be passed to his brother .\nSent 4: Shahryar therefore orders Grand Vizier Ja'Far ( ( ( Jim Carter to bring him a harem girl to marry and then have executed the next day .\nSent 5: In order to prevent this , the Grand Vizier 's clever daughter , Scheherazade , decides to marry the Sultan herself .\nSent 6: Scheherazade has a plan to prevent her execution and at the same time cure the Sultan of his madness .\nSent 7: With the help of some tutoring from a bazaar storyteller , Scheherazade tells the Sultan a story every night , stopping at dawn with a cliffhanger and refusing to continue until dusk .\nSent 8: Shahryar must therefore let Scheherazade live for another day in order to hear the rest of the story .\nSent 9: Cunningly , Scheherazade has hidden a moral within every story , to bring the Sultan out of his madness .\nSent 10: Meanwhile , Schahzenan hears about the Sultan 's madness and that he is unable to execute Scheherazade .\nSent 11: Perceiving this as weakness , Schahzenan leads his army to Baghdad in an attempt to take the throne by force .\nSent 12: However , by the time Schahzenan 's army reaches the city , Scheherazade 's plan has worked .\nSent 13: As a result of her stories , Shahryar has overcome his madness and has fallen in love with Scheherazade . \nQuestion: who had a deep distrust for all women because he was betrayed by his wife?.\nanswer:\n1, 3.\n\n\nquestion:\nParagraph- Sent 1: Moore portrays the NRA as an unethical, dishonest organization; he sees the paranoia and fear in the United States as a primary cause of violence, and he does not see gun ownership itself as a problem.\nSent 2: His documentary is full of subtle humor, jaw-dropping dialogue and dark contrasts.\nSent 3: All in all, it is an accurate portrayal of America's gun and violence culture.\nSent 4: It also raises questions about America's foreign policy of recent decades, questions which have been all but ignored by Moore's critics.\nSent 5: On your webpage, you state that \"Moore's resolution is questionable.\nSent 6: After all, early in the movie he discards the possibility that playing violent video games and watching violent flicks can cause violence -- because Canadians like, and Japanese positively love, those.\nSent 7: If violent movies and violent videogames cannot cause violence -- then how can newscasts about violence do so?\"Sent 8: This is a faulty generalization.\nSent 9: If, as Moore implies (although never states as fact), video games and violent movies are relatively harmless, it does not logically follow that all types of media presentation are harmless.\nSent 10: There is a huge difference, for example, between playing a game like \"Quake\" and listening to a radio broadcast that tells you that your family will be killed unless you take action to kill others now.\nSent 11: The latter is the kind of media propaganda that was used to unleash a genocide in Rwanda in 1994, which killed 800,000 people.\nSent 12: Similarly, the main motivation for the crusades (beyond the promise of wealth) was that Christians were supposedly being slaughtered and had to be saved.\nSent 13: Obviously, media propaganda can incite people to kill.\nSent 14: Interactive fiction like video games, on the other hand, presents violence in a narrative context, which may very well desensitize participants to said violence, but no causative link has ever been proven.\nSent 15: Moore's hypothesis (which apparently comes at least in part from the book \"Culture of Fear\" by Barry Glassner, also advertised on Moore's website) is that the constant bombardment with messages of fear can incite paranoia, which itself can lead to violent acts.\nSent 16: This is consistent with the kind of media-incited violence described above, and in no relationship whatsoever to the theory of video game or music incited violence.\nSent 17: It is no surprise, however, that US (and European) media do not question their own propaganda of fear. \nQuestion: What is a faulty generalization about newscasts?.\nanswer:\n" }, { "from": "gpt", "value": "7, 8.\n\n\n" } ]
[ { "from": "human", "value": "Teacher:Given a set of five words, generate the word from the set that does not belong (i.e. is the least relevant) with the other words. Words are separated by commas.\nTeacher: Now, understand the problem? Solve this instance: jetstream, blue, flow, current, detests\nStudent:" }, { "from": "gpt", "value": "detests" } ]
[ { "from": "human", "value": "In this task, you are given an input list A. You need to find all the elements of the list that are alphabets in the same order as they appear in the list A. Do not change their case/capitalization.\nExample: ['238', 'h', '92', 'U', '2799']\nExample solution: h, U\nExample explanation: Here, the alphabetical elements in the input list in order are 'h' and 'U'.\n\nProblem: ['4097', 'Y', 'J', '8245', 'A', '3351', 'j', 'I']\n" }, { "from": "gpt", "value": "Solution: Y, J, A, j, I" } ]
[ { "from": "human", "value": "In this task, you're given a review from Amazon and rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral, 4: good, 5: extremely good. Your task is to generate whether the rating matches the review or not. Answer with \"True\" if the sentence belongs to that section, otherwise answer with \"False\"\nExample: Review: These are junk! Both bulbs have burned out within a two month period!! I cannot believe that this company can be in business with such poor quality. I have used infrared lights for my ball python for many years now and I get a varied range of months from a bulb, but I have never gone through two bulbs in a matter of two months! I am very disappointed. \n Rating: 1\nExample solution: True\nExample explanation: The user seems very disappointed in the product because the bulb they ordered has been burned out earlier than usual. So, he gave 1 star to the review considering it extremely poor. So, true is the correct answer.\n\nProblem: Review: Looks cheap. He didnt care of course. He liked it. But I prefer to wear things that look and feel of quality. It also runs large. Overall, waste of $$ \n Rating: 1\n" }, { "from": "gpt", "value": "Solution: True" } ]
[ { "from": "human", "value": "You are given a short text as a title. Your task is to generate a poem as output that is related to the given title and should feel like written by kids. The output should be a run-on sentence (two or more complete sentences connected without any punctuation). The poem should not be too long or too complex, because it should feel like it is written by younger person without high level of literature education.\n\nLet me give you an example: Onomatopeia sounds\nThe answer to this example can be: my friend call this morning to hear the different sound she collect them in a bag and call me to her town the singing of the kettle the clanging of the anvil the ringing of the phone the wailing of the siren\nHere is why: the poem is related to sounds, and is in a style that resembles a poem instead of other kind of texts.\n\nOK. solve this:\nTHE CAT AND RAT\nAnswer:" }, { "from": "gpt", "value": "the cat sit on that rat with a mat they have a chat with a bat the bat have a hat and would pat the hat" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, you are given a list of integers and an integer k. You need to add integer k to each element in the list and return the updated list.\nPROBLEM: [260, 42, 210, 144, 29, 129, 19, 149, 70, 15, 211, 170, 130, 104, 231, 81, 124, 158, 258, 82] k=12\n\nSOLUTION: [272, 54, 222, 156, 41, 141, 31, 161, 82, 27, 223, 182, 142, 116, 243, 93, 136, 170, 270, 94]\n\nPROBLEM: [275, 287, 291, 197, 119, 145, 79, 46, 123, 66, 133, 115, 262, 130, 105, 272, 125, 253, 83, 290] k=12\n\nSOLUTION: [287, 299, 303, 209, 131, 157, 91, 58, 135, 78, 145, 127, 274, 142, 117, 284, 137, 265, 95, 302]\n\nPROBLEM: [266, 195, 219, 253, 97, 116, 180, 229, 34, 142, 173, 12, 182, 127, 150, 45, 245, 167, 177, 151] k=7\n\nSOLUTION:" }, { "from": "gpt", "value": "[273, 202, 226, 260, 104, 123, 187, 236, 41, 149, 180, 19, 189, 134, 157, 52, 252, 174, 184, 158]\n\n" } ]
[ { "from": "human", "value": "instruction:\nIn this task, you are given a dialogue between a user and an assistant, where users and assistants converse about geographic topics like geopolitical entities and locations. The task here is to find if the dialogue is by the user or assistant. Classify your answers into user and assistant.\nquestion:\nSure, Honduras is considered a low middle-income nation by the World Bank. Also, most Honduran farmers live in extreme poverty at or below 180 US dollars per capita.\nanswer:\nassistant\n\n\nquestion:\nWhat can you tell me about San Marino\nanswer:\nuser\n\n\nquestion:\nScotland has a long military tradition predating its union with England, it is currently part of the British Armed Forces. There are Several Military Submarines housed of the shores of Scotland.,\nanswer:\n" }, { "from": "gpt", "value": "assistant\n\n\n" } ]
[ { "from": "human", "value": "Definition: Given a set of five words, generate the word from the set that does not belong (i.e. is the least relevant) with the other words. Words are separated by commas.\nInput: relaxed, jail time, annoyed, fine, well\nOutput:" }, { "from": "gpt", "value": "jail time" } ]
[ { "from": "human", "value": "Based on the given context, craft a common-sense question, especially those that are LONG, INTERESTING, and COMPLEX. The goal is to write questions that are easy for humans and hard for AI machines! To create such questions, here are some suggestions: A. What may (or may not) be the plausible reason for an event? B. What may (or may not) happen before (or after, or during) an event? C. What may (or may not) be a plausible fact about someone (or something)? D. What may (or may not) happen if an event happens (or did not happen)? You can also create other types of questions. DO NOT make your question answerable without looking at the context, or question of which the correct answer can be directly extracted from the context. DO NOT ask a question that requires very specialized knowledge that is not common sense. DO NOT ask too simple or too short questions. Your question must be related to the context and answerable with common sense. Try to add more variations and complexity to the questions.\nExample: Context: I was told, in person over the phone, that my shoes were on their way. They have my money. I have no shoes.\nExample solution: What may happen before I called them?\nExample explanation: The question can not be answered directly from context and requires commonsense.\n\nProblem: Context: All I needed to do was to turn the door knob and the door would open up for me . There are times when I thought of yelling that I ' m home , but I never did it , because it would n't feel right . And Junsu , he would either be sitting watching some kind of show on television or playing video games , mostly it was video games . But today , no matter how many times I tried , the door would n't open . No matter for how long I stood there knocking , no one would open .\n" }, { "from": "gpt", "value": "Solution: Why is the narrator starting to get anxious ?" } ]
[ { "from": "human", "value": "instruction:\nIn this task, you will be shown a short story with a beginning, two potential middles, and an ending. Your job is to choose the middle statement that makes the story incoherent / implausible by indicating 1 or 2 in the output. If both sentences are plausible, pick the one that makes less sense.\nquestion:\nBeginning: Cindy wanted to drink with her friends. Middle 1: Cindy carefully monitored how much she drank. Middle 2: Cindy did not monitor how much she drank. Ending: She had gotten alcohol poisoning from too much liquor.\nanswer:\n1\n\n\nquestion:\nBeginning: Bill visited the local zoo. Middle 1: Bill was impressed with the animal environments. Middle 2: Bill was very unimpressed with the animal environments. Ending: He told his friends about the zoo and brought them there later.\nanswer:\n2\n\n\nquestion:\nBeginning: I got pulled over on my way home from work. Middle 1: I got a ticket for a broken light. Middle 2: I got a ticket for speeding. Ending: He simply told me to make sure I got it fixed soon.\nanswer:\n" }, { "from": "gpt", "value": "2\n\n\n" } ]

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.