Split (1)

train · 8.3M rows

Search is not available for this dataset

conversations listlengths 2 2
[ { "from": "human", "value": "Detailed Instructions: Given a disfluent sentence, modify the sentence to it to its equivalent fluent form, preserving the meaning of the sentence.\nProblem:Le Grande also stated or uh wrote that defining the term civil disobedience so difficult it could be described as?\nSolution:" }, { "from": "gpt", "value": "Le Grande also wrote that defining the term civil disobedience so difficult it could be described as? " } ]
[ { "from": "human", "value": "Teacher:In this task, you are given sentences from movie reviews. The task is to classify a sentence as \"POS\" if the sentiment of the sentence is positive or as \"NEG\" if the sentiment of the sentence is negative\nTeacher: Now, understand the problem? Solve this instance: Tsai convincingly paints a specifically urban sense of disassociation here .\nStudent:" }, { "from": "gpt", "value": "POS" } ]
[ { "from": "human", "value": "You are given a question or fill-in-the-blank question, two answer options (Option1 and Option2) and an Explanation. Your task is to find the correct answer (return the string of the correct option, not option1/2) for the given question from the given options and using explanation.\nOne example is below.\nQ: Question: The government of Canada is considering implementing less carbon taxes across the country. If these taxes were implemented, the amount of carbon dioxide emissions in the country would be expected to \n Option1: fall \n Option2: rise \n Explanation: The carbon taxes encourage people to use less fossil fuel, which reduces carbon dioxide emissions.\nA: rise\nRationale: As mentioned in the Qualitative Statement, due to taxes people will reduce usage of fossil fuel and hence, carbon dioxide emission will also reduce. So, if Camada government decrease the tax, people will use it more and hencce, emission will also incerase.\nQ: Question: Which two objects likely have the greatest gravitational force between them? \n Option1: Earth and Neptune \n Option2: Jupiter and Neptune \n Explanation: This is because the gravitational force of attraction between the Earth and Sun is stronger when the Earth is closer to the Sun.\nA:" }, { "from": "gpt", "value": "Jupiter and Neptune" } ]
[ { "from": "human", "value": "Teacher:In this task, you will be presented with a question about part-of-speech tag of a word in the question. You should write an implausible POS tag to the question. Even though there exist multiple wrong answers, we only need a single wrong answer. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb\nTeacher: Now, understand the problem? Solve this instance: What is the part-of-speech tag of the word \"of\" in the following question: How tall is this American former professional basketball player born on January 22 , 1988 who is from the state capital and most populous city of the U.S. state of Indiana ?\nStudent:" }, { "from": "gpt", "value": "JJ" } ]
[ { "from": "human", "value": "Definition: You'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.\nInput: Context Word: pool. \nQuestion: PersonX liked to be outside more than PersonY so _ spent time arguing for getting a pool. \nAnswer: PersonX\nOutput:" }, { "from": "gpt", "value": "PersonX liked to be outside more than PersonY so _ spent time arguing against getting a pool." } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you're given a review from Amazon's food products. Your task is to generate a short summary of the given review in the input. Note that you don't need to write a complete sentence as a summary.\n\nMy dogs love Newman's the Chicken and the Peanut Butter treats, but didn't care for these treats. They are about 1.5 inch square and very difficult to break in two. I felt they were too big and solid to give to the dogs. After several attempts to entice them with the treats and no happy response, I tossed them. I will stick to the other Newman's treats.\n" }, { "from": "gpt", "value": "Newman's Lamb and Barley Treats" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nYou 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.\nExample: I have bought several of the Vitality canned dog food products and have found them all to be of good quality. The product looks more like a stew than a processed meat and it smells better. My Labrador is finicky and she appreciates this product better than most.\nOutput: Positive\nIt's a positive review because the owner of the dog is satisfied with the product and mentioned that their dog appreciates the product.\n\nNew input case for you: I know others like salt more than I do but I am not on a salt free diet or anything like that. I love sausage but this was way too salty for my taste.\nOutput:" }, { "from": "gpt", "value": "Negative" } ]
[ { "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.\nGenerate an appropriate title for the given text. The generated title must be short and include the main topic of the text. The preferred titles are under fifteen words.\n\nBut Eluned Morgan conceded that it would be \"difficult for us to stop\" from a legal point of view. Her comments were criticised by a Labour AM. Alun Davies said threatening legal action \"sounds like the last breath before you're thrown out of the pub\". Mr Davies said he was not convinced the Welsh Government would \"have a leg to stand on\" in trying to shape international trade deals after Brexit. Following Donald Trump's comments during last week's trade visit that the NHS would be \"on the table\" in any future trade talks between the UK and the USA, Eluned Morgan said there was \"absolutely no prospect whatsoever of us allowing the Welsh NHS to be part of any negotiation.\" The US President then rowed back on his initial comments following criticism from a number of MPs. Asked about her response to President Trump's remarks as she gave evidence to the Assembly's Brexit committee on Monday, Ms Morgan said \"legally, it would be difficult for us to stop because we don't have a veto over trade\". \"Politically, I think it's extremely unlikely to happen,\" the international relations and the Welsh language minister said. \"They [the UK Government] should not be concluding any trade agreements without consulting us where we have the power.\" Ms Morgan explained that UK and Welsh government officials are working on an agreement or 'concordat' for how future trade deals are negotiated. During a robust exchange, the Labour AM Alun Davies said: \"I want something which is in law to which I can hold you to account and which colleagues in Westminster can hold the UK Government to account. \"The argument we'll make life difficult for them, it sounds alright on the street, but it's not the reality of intergovernmental relations.\" \"The United Kingdom has to find a way of functioning. \"At the moment, your answers aren't giving me any confidence that there is that structure in place because, if the Welsh Government's argument is, 'we'll see you in court', it's not a very impressive argument either for the continuation of the structure of United Kingdom as a state or the commitment of the government within the United Kingdom to actually work together,\" he added. Responding to the criticism, Ms Morgan said: \"Is the current intergovernmental structure adequate? \"Absolutely not... and it's not just in relation to trade, it's in relation to almost every aspect of government policy. So, that infrastructure needs to be built.\"\nSolution: NHS Wales: Court action if trade deals affect service?\nWhy? The output phrase is the appropriate title for the given text and it highlights the essence of the passage.\n\nNew input: Criticising the growth of the prison population in England and Wales, he said there must be other penalties. The new measures will involve paying private firms and voluntary groups according to how many prisoners they rehabilitate. He said locking people up for the sake of it was a waste of public funds. David Cameron defended the plans during prime minister's questions and said it was now time for \"radical reform\" of the prison service. But former Conservative Home Secretary Michael Howard has told Radio 4's PM programme he was \"not convinced\" by Mr Clarke's suggestion that fewer criminals should be sent to prison. 'Victorian England' In his first major speech since taking office, Mr Clarke said prison had too often proved \"a costly and ineffectual approach that fails to turn criminals into law-abiding citizens\". Speaking in London he said: \"More than half of the crime in this country is committed by people who have been through the system. We must now take action and shut off this revolving door of crime and reoffending. \"We need a more constructive approach that tackles this head-on. An intelligent and transparent approach to sentencing that targets the causes of reoffending, so making our communities safer and better places to live. We describe it as a rehabilitation revolution.\" Mr Howard, who was home secretary from 1993 to 1997, said he stood by his \"prisons work\" speech given to the 1993 Conservative Party conference. Stressing that he was expressing his personal opinion, he said: \"I've read [Mr Clarke's] speech. \"I'm not convinced by it. \"I think in order to protect the public, serious and persistent criminals need to be put in prison. \"I think that is what conscientious judges and magistrates are doing at present and I think that is the best way of protecting the public.\" The prime minister said the prison service was \"not working properly\" at the moment. He said: \"When you've got these reoffending rates, when you've got the cost of each prison place, when you've got the appalling problem of drugs in prisons, we have got to reform.\" He added: \"If ever there was part of our public services that needed radical reform to make sure prison does work, then now that's it.\" In May the prison population in England and Wales reached a record high of 85,201. That is almost twice the figure in 1992, when Mr Clarke was last in charge of prisons as home secretary. It was an increase he said he would have dismissed as \"impossible and ridiculous\" if someone had predicted it at the time. Earlier, speaking on BBC Radio 4's Today programme, Mr Clarke said a sentencing review based on punishment and protecting the public was needed. Criticising the increase of the prison population under Labour, he added: \"[Former Home Secretaries] David Blunkett and John Reid had a chequebook in one hand and a copy of the Daily Mail in the other.\" The government plans to use the voluntary and private sectors to rehouse, rehabilitate and find work for released prisoners, with bodies only paid if their efforts lead to a significant fall in reoffending. These reforms will hopefully pay for themselves by reducing the costs elsewhere within the criminal justice system, Mr Clarke added. 'Stunning successes' But shadow home office minister David Hanson said Mr Clarke needed to back his ideas with a better prisons budget. \"Where Ken Clarke has a point is that there are people who go through the system who revolve through that door who have long-term drug, alcohol, employment problems - who need to be reformed to get back into society in a positive way,\" he said. \"But where I disagree with Mr Clarke is that it takes resources. And he is now planning to cut the resources to the justice department and to probation by 25% over the next four years.\" And shadow justice minister Jack Straw said the increased number of offenders sentenced to prison had been a key factor in reducing crime. \"Does anyone seriously believe that crime would have come down and stayed down without these extra prison places?\" he wrote in the Daily Mail. The general secretary of the Prison Governors Association, Paddy Scriven, said jails had some \"stunning successes\" with inmates who spent more than six months behind bars. \"If we're left to concentrate on that and the shorter sentenced prisoners become the responsibility of a properly-funded probation service, then ...we're cutting costs and looking after the public in the way that we should be,\" he said. 'Poor value for money' In a statement, the Probation Chiefs Association said it supported Mr Clarke's plans and said the next step for the service should be a \"flexible strategic framework free of overly bureaucratic control and interference\". Juliet Lyon, of the Prison Reform Trust, said the system needed change as it was not working. \"You only have to look at the reconviction rates for those short sentence people - over 60% reconvicted within a year of release - to realise that we've got very poor value for money,\" she said. Reoffending rose by 8% for adults between 2006 and 2008, and nearly half of offenders sent to prison are reconvicted within a year. Meanwhile, MSPs have passed proposals to vastly reduce the number of prison sentences of three months or less at the Scottish Parliament, despite opposition from Conservatives. The measure, which will introduce a presumption against the shorter sentences by sheriffs, was voted through in the Criminal Justice and Licensing Bill by MSPs at Holyrood.\nSolution:" }, { "from": "gpt", "value": "Justice Secretary plans 'radical' prison policy change" } ]
[ { "from": "human", "value": "Given a piece of financial news and its polarity, classify it into 'true' if the polarity is correct and classify into 'false' if the polarity is incorrect. Output must be 'true' or 'false'. \n\nExample input: news:According to Gran , the company has no plans to move all production to Russia , although that is where the company is growing .\npolarity:neutral\nExample output: true\nExample explanation: Although the author uses negative words like 'no' in the news, there is no evidence of the news begin positive or negative for any stakeholder. Hence, the polarity is neutral and the output is True.\nQ: news:The financial details of the transaction were not disclosed .\npolarity:positive\nA:" }, { "from": "gpt", "value": "false" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task you will be given two lists of numbers and you need to calculate the intersection between these two lists. The intersection between two lists is another list where every element is common between the two original lists. If there are no elements in the intersection, answer with an empty list. Your list of numbers must be inside brackets. Sort the numbers in your answer in an ascending order, that is, no matter what the order of the numbers in the lists is, you should put them in your answer in an ascending order.\nPart 2. Example\n[2,5,1,4],[2,5,8,4,2,0]\nAnswer: [2,4,5]\nExplanation: The elements 2,4, and 5 are in both lists. This is a good example.\nPart 3. Exercise\n[3, 8, 2, 2, 9, 5, 10, 4, 9] , [2, 5, 7, 8, 9, 1, 6, 1, 6]\nAnswer:" }, { "from": "gpt", "value": "[2, 5, 8, 9]" } ]
[ { "from": "human", "value": "Instructions: In this task, you must classify if a given review is positive/negative, indicating your answer as P or N.\nInput: dreamworks pictures presents a jinks/ cohen company production kevin spacey annette bening \" american beauty \" thora birch allison janney peter gallagher mena suvari wes bentley and chris cooper co - producers stan wlodkowski alan ball music by thomas newman costume designer julie weiss\nfilm editor tariq anway chris greenbury production designer naomi shohan director of photography conrad\nl . hall , a .\ns .\nc .\nproduced by bruce cohen & dan jinks written by alan ball directed by sam mendes\n\" both my wife and daughter think i 'm this gigantic loser .\nand they 're right .\ni have lost something .\ni did n't always feel this sedated .\n\" with that piece of dialogue , we are fully introduced to lester burnham ( kevin spacey ) , a 42 year old man trapped within his own life .\nlester works for an advertising agency .\nhis growing dissatisfaction with his job is only one of the mid - life crisis he is suffering .\nestranged from both his wife and his daughter , lester starts to crack under the stress .\nhis life becomes nothing more than a series of mastubatory fantasies , and sullen apathy .\ncarolyn burnham ( annette bening ) , is the prototypical career woman/ homemaker .\nshe carefully tends her rose garden , decorates her home with the best furnishings .\nbut inside she is desperate .\nunsuccessful at her profession as a real estate agent , she drives herself into states of denial and self loathing that only feed her growing resentment towards her family .\nthe third member of this anti - family is jane burnham ( thora birch ) , lester and carolyn 's daughter .\na young girl going through the typical stages of adolescence , but having to also come to terms with her families growing dysfunction .\nthis funny ( and frightening ) slice of life is refreshingly simple .\nnot one character is given less than is needed to identify him or her .\nsome of the most telling characters are those that serve to highlight other characters .\nmost notably is barbara fitts ( allison janney ) , the almost catatonic wife of retired marine colonel fitts .\nshe has almost no dialogue , and seems to be either recovering from a stroke or suffering from one .\ncolonel fitts ( chris cooper ) is an angry and frightened man .\nhis rage directed almost singularly at his son , ricky ( wes bentley ) who has just moved with his family to the same neighborhood as the burnham 's .\nin fact they are the next door neighbors .\nanymore detail into the personalities of these marvelously diverse characters would deprive one of the many pleasures and surprises to be had in \" american beauty \" .\nalan ball , who was the co - executive producer of the hit tv series \" cybil \" and creator of the new sitcom\n\" oh grow up \" , has fashioned one of the most insightful and expertly tuned screenplays to have hit the screen in the past ten years . not one character in this film rings falsely .\nand the depth of personality in each , is achingly honest and insightful .\nthe plot detailing the last year in the life of a man as he tries to find his own self worth is so resoundingly cliched and at the same time original as to bring to mind such marvelous film work as \" the graduate \" or \" lolita \" .\nkevin spacey turns in one of this years most pragmatic performances .\nhis lester burnham is an everyman caught up in the middle of a life that is spiraling into old age .\nfinally unable to deal with the lost soul that he has become , lester tries to return to his youth .\nhe quits his job ( actually blackmailing his employer for one year 's salary ) , starts smoking pot , fantasizes about his daughter 's girlfriend angela ( mena suvari , in a marvelous performance here ) , starts working out , and finally takes a job at the local fast food outlet .\nmr .\nspacey 's performance is so remarkably subtle and ingenuous , that we can be certain that come oscar ? time ,\nwe can be assured to see him name among the five nominees .\nannette bening also turns in what may be the best performance of her career .\ncarolyn burnham is a woman who has become so insecure as to be caught up in maintaining the facade of normalcy . unable to cope with her growing disillusionment , she forces herself to maintain her demeanor , driving her further and further into desperation , adultery and possibly murder .\nms .\nbening makes the character of carolyn so compelling as to be identifiable to almost anyone .\nthe slow and methodical turn from happy home maker to charnel house martha stewart is too frightening to express in words .\nthora birch holds her own against the talents cast with her .\njane burnham is both an innocent girl caught up in what is a dysfunctional family , and a rebellious child ready to abandon them at any moment .\nher growing distrust and isolation from her family is something that many parents should view as a warning .\nshe is the prototypical trophy child .\nwhen carolyn praises her daughter after a performance by her cheerleading team ( \" i 'm so proud of you , honey .\nyou did n't screw up once ! \" ) , the bitterness and resentment are palpable .\nthora birch is a young actress to watch\n. praise must also go to chris cooper who brings yet another angry father role to life with depth and resonance .\ncolonel finn is a man in complete denial .\nhis military upbringing masking a desire he is too repulsed to even comprehend .\nwes bentley as ricky finn is fine as the enigma .\nthe boy next door who may be more foe than friend .\na deceitful and calculating young man , whose voyeuristic proclivities mask a deeper and more profound understanding of life than any of the adults around him .\nmr .\nbentley 's performance is the one troublesome note in the film .\nthat is simply because the character is such a grand and complete liar , that one almost faults the performance for it .\ndirector sam mendes handles all of the particulars of the cast and the settings with a sure and composed style that is neither intrusive nor subtle .\nscenes of carolyn walking through the rain , carry an ominous fission that calls attention to the emotions of the character .\nthe subtle cinematography by conrad hall is wonderful , capturing the season in all of it 's harsh beauty\n( fall has never looked so inviting , yet depressing ) .\nevery nuance of \" american beauty \" begs it 's audience to think and examine .\nit is a film that will be discussed and debated for years to come .\nand well it should , as\nit is simply one of this years best .\nOutput:" }, { "from": "gpt", "value": "P" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGenerate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words.\n\nSentence1: a cavern is formed by carbonic acid in groundwater seeping through rock and dissolving limestone. \nSentence2: Carbonic acid dissolves limestone by separating the calcium and carbonate and creating a liquid.\nOutput:" }, { "from": "gpt", "value": "carbonic" } ]
[ { "from": "human", "value": "In this task, you need to count the number of words in a sentence that end with the given letter. Answer with numbers and not words.\n\n[EX Q]: Sentence: 'a brown and white cow wearing a bell around its neck near a restaurant'. How many words end with the letter 'd' in the sentence.\n[EX A]: 2\n\n[EX Q]: Sentence: 'a laptop computer that is on a desk'. How many words end with the letter 'a' in the sentence.\n[EX A]: 2\n\n[EX Q]: Sentence: 'for jets planes flying in the big blue sky'. How many words end with the letter 'e' in the sentence.\n[EX A]:" }, { "from": "gpt", "value": "2\n\n" } ]
[ { "from": "human", "value": "In this task you are given an anecdote, which recount a complex ethical situation. The question you are given is, has the author of the anecdote acted ethically? answer this question with \"RIGHT\" or \"WRONG\".\nQ: All residents of my apartment building have a key fob to access the main lobby and get to their home. If someone is behind me, I try to pay attention to see if 1) I recognize them and know that they live in the building, or 2) they're holding their own key fob. If it's one of these two things, I hold the door open for them.\n\nThis one time, there was someone behind me that I've never seen before. They weren't holding a key fob, they were just walking behind me. I opened the door and made no effort to hold the door for them. If this was a public place, I wouldn't have an issue holding it open for them. This person got incredibly mad at me, practically yelling how unbelievably rude I was. It made for an interesting elevator ride up.\n\nI've also lived in a building that had underground parking. There's a large sign that says \"please wait until the gate closes before driving off\". I feel like this is so people who don't live in the building can't gain access. Isn't this the same thing?\nA: " }, { "from": "gpt", "value": "RIGHT" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you are given the abstract of a research paper. Your task is to generate a summary of this abstract. Your summary should not be very short, but it's better if it's not more than 30 words.\n\nWith the rise in employment of deep learning methods in safety-critical scenarios, interpretability is more essential than ever before. Although many different directions regarding interpretability have been explored for visual modalities, time-series data has been neglected with only a handful of methods tested due to their poor intelligibility. We approach the problem of interpretability in a novel way by proposing TSInsight where we attach an auto-encoder with a sparsity-inducing norm on its output to the classifier and fine-tune it based on the gradients from the classifier and a reconstruction penalty. The auto-encoder learns to preserve features that are important for the prediction by the classifier and suppresses the ones that are irrelevant i.e. serves as a feature attribution method to boost interpretability. In other words, we ask the network to only reconstruct parts which are useful for the classifier i.e. are correlated or causal for the prediction. In contrast to most other attribution frameworks, TSInsight is capable of generating both instance-based and model-based explanations. We evaluated TSInsight along with other commonly used attribution methods on a range of different time-series datasets to validate its efficacy. Furthermore, we analyzed the set of properties that TSInsight achieves out of the box including adversarial robustness and output space contraction. The obtained results advocate that TSInsight can be an effective tool for the interpretability of deep time-series models.\n" }, { "from": "gpt", "value": "We present an attribution technique leveraging sparsity inducing norms to achieve interpretability." } ]
[ { "from": "human", "value": "Definition: You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. Your task is to classify the conversation either convey 'No emotion' or 'Happiness' by providing '1' and '0', respectively.\nInput: Person1: I need help preparing for my presentation on Friday . \n Person2: I could help you with that . \n Person1: Are you sure you have the time ? \n Person2: I promise you that I have the time to do this . If I didn't , I wouldn't offer to help . \n Person1: What would be the best time for you to help me ? \n Person2: Tomorrow night would work for me . \n Person1: Should we just meet here ? \n Person2: OK , and I'll bring some information that helped me with my presentation . \n Person1: I'll see you then . \n Person2: See you tomorrow night . \nOutput:" }, { "from": "gpt", "value": "0" } ]
[ { "from": "human", "value": "Detailed Instructions: You need to answer a given question containing a blank (_). Your answer must be one of the two objects mentioned in the question, for example \"trophy\" and \"suitcase\". Your answer must not contain a word that is not present in the question. Please don't use articles (e.g., the, a) before the answer.\nQ: James could have filled the tank with more gas before stopping. The _ is very big.\nA:" }, { "from": "gpt", "value": "tank" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task you are given a small conversation between two persons and 4 options on how the conversation should continue. Your job is to choose the most reasonable option. The conversation and the options are separated by a newline character. Each dialogue in the conversation are separated by a comma. F and M indicate female and male, respectively.\n\nF: Tom, do you like stories? ,M: Yes, very much. You know I spent my childhood with my grandparents in the countryside. They often told me stories. ,F: Do you have any story books now? ,M: Yes. Last year my friend bought me a collection of stories as a birthday present. It is so interesting that I have read it 3 times. ,F: Oh, could I borrow it from you? ,M: Certainly, I put it in a drawer in the living room. I will get it for you now.\n(A) F: Haha, why you put the collection of stories on the table in the kitchen? (B) F: You must like the collection of stories very much because you put it in a box in the dining room. (C) F: Thank you, now that you put it in a drawer in your living room, why don't you read it? (D) F: I am sorry. You spoke so rapidly that I did not catch the meaning of what you said. Could you repeat that?\nOutput:" }, { "from": "gpt", "value": "D" } ]
[ { "from": "human", "value": "Q: In this task, You are given an amazon food product review and its summary. Your task is to Generate \"True\" if given review and its summary match, otherwise generate \"False\".\nI was excited for these. Got them on a Monday, on Tuesday I came in and my husband tells me you have to try these they are excellent. So I'm like Ok, I reach in the bag and I'm like ewwwww they feel slimey but none the less popped one in my mouth. I almost puked, I spit it right out terrible, disgusting, don't buy these. I love Amazon and buy a ton of stuff from them but these are a definite NO! I might add this was a joke to my husband because he had ate one and had to spit it out! He was just wanting to watch me eat one. :( \n Summary: Awful Texture and Taste\nA:" }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nGiven a scientific passage and an answer, generate a question for the given answer.\nExample: Passage: A frameshift mutation is a deletion or insertion of one or more nucleotides that changes the reading frame of the base sequence. Deletions remove nucleotides, and insertions add nucleotides. Consider the following sequence of bases in RNA:. Answer: nucleotides.\nOutput: A frameshift mutation is a deletion or insertion of one or more of what that changes the reading frame of the base sequence?\nThe science passage defines frame mutation and the main compoment here is nucleotides. Hence the generated question is apt.\n\nNew input case for you: Passage: The inner ear is often described as a bony labyrinth, as it is composed of a series of canals embedded within the temporal bone. It has two separate regions, the cochlea and the vestibule, which are responsible for hearing and balance, respectively. The neural signals from these two regions are relayed to the brain stem through separate fiber bundles. However, these two distinct bundles travel together from the inner ear to the brain stem as the vestibulocochlear nerve. Sound is transduced into neural signals within the cochlear region of the inner ear, which contains the sensory neurons of the spiral ganglia. These ganglia are located within the spiral-shaped cochlea of the inner ear. The cochlea is attached to the stapes through the oval window. The oval window is located at the beginning of a fluid-filled tube within the cochlea called the scala vestibuli. The scala vestibuli extends from the oval window, travelling above the cochlear duct, which is the central cavity of the cochlea that contains the sound-transducing neurons. At the uppermost tip of the cochlea, the scala vestibuli curves over the top of the cochlear duct. The fluid-filled tube, now called the scala tympani, returns to the base of the cochlea, this time travelling under the cochlear duct. The scala tympani ends at the round window, which is covered by a membrane that contains the fluid within the scala. As vibrations of the ossicles travel through the oval window, the fluid of the scala vestibuli and scala tympani moves in a wave-like motion. The frequency of the fluid waves match the frequencies of the sound waves (Figure 14.6). The membrane covering the round window will bulge out or pucker in with the movement of the fluid within the scala tympani. Answer: inner ear\nOutput:" }, { "from": "gpt", "value": "What part of the ear is often described as a bony labyrinth?" } ]
[ { "from": "human", "value": "You are supposed to identify the category of a high-school level math question. There are five possible categories (1) algebra (2) arithmetic (3) measurement (4) numbers, and (5) probability. Use the following guidelines: (1) 'algebra' questions will typically contain letter variables and will ask you to find the value of a variable (2) 'arithmetic' questions will ask the sum, difference, multiplication, division, power, square root or value of expressions involving brackets (3) 'measurement' questions are questions that ask to convert a quantity from some unit to some other unit (4) 'numbers' questions will be about bases, remainders, divisors, GCD, LCM etc. (5) 'probability' questions will ask about the probability of the occurrence of something. A question must belong to only one category.\n\nSuppose 0 = t - 3j + j - 8, -4 = t - 5j. What is the highest common divisor of t and 16?" }, { "from": "gpt", "value": "numbers" } ]
[ { "from": "human", "value": "In this task, you are given a pair of action statements. Your task is to check if you can conclusively identify which statement is less ethical or not. Answer: 'no' if one of the statements is less ethical, and 'yes' otherwise.\n\nACTION1: not wanting my parents to use my car ACTION2: expecting sex from my girlfriend" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, You are given an amazon food product review and its summary. Your task is to Generate \"True\" if given review and its summary match, otherwise generate \"False\".\nSee one example below:\nProblem: I have bought several of the Vitality canned dog food products and have found them all to be of good quality. The product looks more like a stew than a processed meat and it smells better. My Labrador is finicky and she appreciates this product better than most. \n Summary: Good Quality Dog Food\nSolution: True\nExplanation: The customer talked about dog food which was good. So, it's a correct Summary. So, the correct answer is true.\n\nProblem: Great Chips - No after taste... Seem to be much better for me. Need to buy the big bags now. \n Summary: Great Chips - Love the Salt & Vinegar\nSolution:" }, { "from": "gpt", "value": "True" } ]
[ { "from": "human", "value": "Teacher: In this task, you will be presented with a question and you have to answer the question based on your knowledge. Your answers should be as short as possible.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nWho were the builders of the mosque in Herat with fire temples ?\nSolution: Ghurids\nReason: This is a good example. Ghurids were the builders of the mosque in Herat with fire temples.\n\nNow, solve this instance: What company took over the station with the lowest UHF number ?\nStudent:" }, { "from": "gpt", "value": "Viacom" } ]
[ { "from": "human", "value": "In this task, you will be given a passage, a question and a list of single-word events identified from the passage. The goal is to point out all events from the given event list that can answer the question. If a question is unanswerable or none of the events answer the question, output should be empty.\nExample: Passage: I submitted the hit. The hit was approved, and then I was paid. Question: What happened after I submitted the hit? Events: ['submitted', 'approved', 'paid'].\nExample solution: approved, paid\nExample explanation: From the passage, we can infer that events approved and paid happened after the event submitted. Therefore, the answer to this question is \"approved, paid\".\n\nProblem: Passage: China's human rights record received a grilling Tuesday by a top US official here who told the Human Rights Commission that abuses in the country were still widespread. US permanent representative to the UN, Ambassador William Richardson acknowledged that two decades of economic growth had dramatically improved the lives of millions of Chinese. Question: What happened before Tuesday? Events: ['record', 'received', 'grilling', 'Tuesday', 'told', 'abuses', 'permanent', 'acknowledged', 'decades', 'improved', 'lives']\n" }, { "from": "gpt", "value": "Solution: record" } ]
[ { "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: Cells of the site of an infection in a animal no wait plant undergo what process to prevent spread of the disease?\nOutput:" }, { "from": "gpt", "value": "Cells of the site of an infection in a plant undergo what process to prevent spread of the disease?" } ]
[ { "from": "human", "value": "Detailed Instructions: You are given a sentence, a question and two answer options ('A' and 'B'). Your task is to find the correct answer (return the string of the correct option, not 'A' or 'B') for the given question.\nProblem:Sentence: Ada had two snacks, a pretzel and a piece of licorice. She noticed that the licorice could bend easily but the pretzel could not. Question: Which one was less likely to break when she bent it? (A) pretzel (B) licorice\nSolution:" }, { "from": "gpt", "value": "licorice" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nYou will be given one or more triples. The second part of each triple shows the relation between the first and the third element. Your task is to write a simple and short piece of text (sentence(s)) that describes the triples in natural language.\nExample: Amsterdam_Airport_Schiphol \| runwayName \| \"09/27 'Buitenveldertbaan'\"\nOutput: Amsterdam Airport Schipol runway name is 09/27 Buitenvelderbaan.\nThe simplest form of input is a single triple. Here the text describes the relationship in natural language.\n\nNew input case for you: Amdavad_ni_Gufa \| location \| Gujarat\nAmdavad_ni_Gufa \| address \| \"Lalbhai Dalpatbhai Campus, near CEPT University, opp. Gujarat University, University Road\"\nAmdavad_ni_Gufa \| completionDate \| 1995\nAmdavad_ni_Gufa \| country \| India\nAmdavad_ni_Gufa \| location \| Ahmedabad\nOutput:" }, { "from": "gpt", "value": "Amdavad, completed in 1995, is located in Ahmedabad, Gujaret, India, at Lalbhai Dalpatbhal Campus, near CEPT University, opp. Gujarat University, University Row." } ]
[ { "from": "human", "value": "Detailed Instructions: You are given a short poem which is written by a kid. Your task is to predict if the kid is in elementary school or high school. Anyone who is from grade 1st to 6th-grade will be considered as in elementary school, and 7th to 12th-grade kids will be considered as in high school. There are only two possible outputs, i.e., elementary and high. All inputs have at least one output and it cannot have both categories at a time.\nSee one example below:\nProblem: he look into your eye that same look just take your breathe away you feel at that moment that he be definitely the one for you but just when you realize that just as fast a he take your breathe away he take your heart and break it into tiny little piece and watch it burn\nSolution: high\nExplanation: The poem is long and linguistically well structured, and the prediction is correct.\n\nProblem: some sister be smart others be dunb some sister work hard others be bum some sister be quiet others be loud some will ashame you and some make you proud there be those who be smart and try talk thing out others do n't think and decide to just shout sister be annoy with sister you 'll fight you 'll argue forever you both want to be right in the very end all sister pull through over all i guess they be there for you\nSolution:" }, { "from": "gpt", "value": "high" } ]
[ { "from": "human", "value": "Definition: In this task, you're given a context, a sentence, and a character. The sentence describes an action or job of the given character. Also, the context provides more information about the sentence or the character. Your task is to return one of the emotions which are expressed by the Character in the given sentence. For that you can use the Context; however, Context is not provided in all the inputs. Also, in some inputs, there can be zero emotion; for that return 'None'.\nInput: Context: Beth had been throwing up for 3 days from the flu. She argued with her mother when she insisted going to the ER. \n Sentence: She finally admitted she needed help. \n Character: Beth\nOutput:" }, { "from": "gpt", "value": "nervous" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you are given a question containing a blank (_) and two options. You should pick the best option to answer the question. Please answer with \"A\" or \"B\".\n\nShe wanted to save more money so she cut back on buying a daily magazine but not coffee because the _ was inessential. (A) magazine (B) coffee\n" }, { "from": "gpt", "value": "A" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nGenerate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words.\nExample: Sentence1: pesticides cause pollution. \nSentence2: pollution can harm animals.\nOutput: pollution.\nThe word \"pollution\" is common to Sentence1 and Sentence2. So, it's a good answer.\n\nNew input case for you: Sentence1: Cynodonts are the therapsids from which mammals evolved. \nSentence2: some therapsids became more mammal-like as they continued to evolve.\nOutput:" }, { "from": "gpt", "value": "therapsids" } ]
[ { "from": "human", "value": "In this task, you're given a statement and three sentences as choices. Your job is to determine which sentence can be inferred from the statement. Incorrect choices change the meaning in important ways or have details that are not mentioned in the statement. Indicate your answer as 1,2, or 3 corresponding to the choice number of the selected sentence.\nQ: Statement: Formal and informal areas are landscaped with pools and fountains, while terraces tumble down the hillsides. Choices: 1. Pools and fountains were used in the landscaping of formal areas. 2. There were no pools or fountains in the informal areas. 3. The architect of the pools and fountains drew inspiration from the gardens of Versailles.\nA: " }, { "from": "gpt", "value": "1" } ]
[ { "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['b', 6785, 't', 'K', 'V', 't', 'L', '855', '881', '6639', '1571', '1027', '8121', 'c', 'K', 'P', '8213', '9377', '2697', '7817', '1715', '911', 'a', 8693, 'A', 'E', 'T', 'Q', 'c', 't', 5405, 'd', 8785, 2703, 'D', 'b', 2965, 4097], ['t', 841, 'c', 6669, 4785, 'u', 'A', 1139, 'X', 'X', 'p', 3085, 't', 'L', '855', '881', '6639', '1571', '1027', '8121', 'c', 'K', 'P', '8213', '9377', '2697', '7817', '1715', '911', 'U', 5917, 'b', 'x']\nAnswer:" }, { "from": "gpt", "value": "t, L, 855, 881, 6639, 1571, 1027, 8121, c, K, P, 8213, 9377, 2697, 7817, 1715, 911" } ]
[ { "from": "human", "value": "This task is about creating an unanswerable question based on a given passage. Construct a question that looks relevant to the given context but is unanswerable. Following are a few suggestions about how to create unanswerable questions:\n(i) create questions which require satisfying a constraint that is not mentioned in the passage\n(ii) create questions which require information beyond what is provided in the passage in order to answer\n(iii) replace an existing entity, number, date mentioned in the passage with other entity, number, date and use it in the question\n(iv) create a question which is answerable from the passage and then replace one or two words by their antonyms or insert/remove negation words to make it unanswerable.\n--------\nQuestion: Passage: The Scotland Act 1998, which was passed by the Parliament of the United Kingdom and given royal assent by Queen Elizabeth II on 19 November 1998, governs the functions and role of the Scottish Parliament and delimits its legislative competence. The Scotland Act 2012 extends the devolved competencies. For the purposes of parliamentary sovereignty, the Parliament of the United Kingdom at Westminster continues to constitute the supreme legislature of Scotland. However, under the terms of the Scotland Act, Westminster agreed to devolve some of its responsibilities over Scottish domestic policy to the Scottish Parliament. Such \"devolved matters\" include education, health, agriculture and justice. The Scotland Act enabled the Scottish Parliament to pass primary legislation on these issues. A degree of domestic authority, and all foreign policy, remain with the UK Parliament in Westminster. The Scottish Parliament has the power to pass laws and has limited tax-varying capability. Another of the roles of the Parliament is to hold the Scottish Government to account.\n\nAnswer: The Scotland Act 2002 extends the devolved what?\n\n\nQuestion: Passage: In the floor, just inside the great west door, in the centre of the nave, is the tomb of The Unknown Warrior, an unidentified British soldier killed on a European battlefield during the First World War. He was buried in the abbey on 11 November 1920. This grave is the only one in the abbey on which it is forbidden to walk.[citation needed]\n\nAnswer: When was The Known Warrior buried?\n\n\nQuestion: Passage: A key aspect of the Gates Foundation's U.S. efforts involves an overhaul of the country's education policies at both the K-12 and college levels, including support for teacher evaluations and charter schools and opposition to seniority-based layoffs and other aspects of the education system that are typically backed by teachers' unions. It spent $373 million on education in 2009. It has also donated to the two largest national teachers' unions. The foundation was the biggest early backer of the Common Core State Standards Initiative.\n\nAnswer:" }, { "from": "gpt", "value": "How much did teachers' unions spend on education in 2009?\n\n\n" } ]
[ { "from": "human", "value": "Instructions: In this task, you're given a passage, further information available on a particular linked term from the statement, and an answer term. Your job is to generate a question that can use the information provided to obtain the given answer. You should use the information on both passage and link information to create the question. Note that the answer to the question should be exactly the given answer, and if the answer is none, the answer to the question shouldn't be obtainable from the passage or linked information.\nInput: Passage: Brown was born on 15 April 1948, in Tangier, Morocco. His father flew Spitfires during World War II and joined civil aviation in the post war period, flying for Gibraltar Airways and British European Airways. He was educated at Merchant Taylors' School, an all-boys public school in Hertfordshire. He then matriculated into St Catherine's College, Oxford to study history. In 1966, he graduated from the University of Oxford with a Bachelor of Arts (BA) degree in Modern History. This was later promoted to Master of Arts (MA Oxon) as per tradition. He remained at St Catherine's to complete a Diploma in Art History. He then undertook post-graduate research at the Courtauld Institute of Art and completed his Doctor of Philosophy (PhD) degree.\n Link Information: GB Airways Answer: GB Airways\nOutput:" }, { "from": "gpt", "value": "Which civil company that Brown's father worked for was founded first?" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task you will be given a list of integers. You should round each integer to the nearest tens place. That means you should round the number to the nearest multiple of 10.\nSee one example below:\nProblem: [-83, 53, -48, 8]\nSolution: [-80, 50, -50, 10]\nExplanation: The output correctly rounds each integer in the input list to the nearest ten. So this is a good example.\n\nProblem: [-190, 891, -453]\nSolution:" }, { "from": "gpt", "value": "[-190, 890, -450]" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a hypothesis and an update. The hypothesis sentence is a statement that speaks of a socially normative behavior. In other words, it is a generalizing statement about how we expect people to behave in society. The update provides additional contexts about the situation that might UNDERMINE or SUPPORT the generalization. An undermining context provides a situation that weakens the hypothesis. A supporting context provides a situation that strengthens the generalization. Your task is to output 'strengthener' or 'weakener' if the update supports or undermines the hypothesis, respectively\n\nHypothesis: It is okay to expect emotional support from your partner at a difficult time.\nUpdate: you are suffering from serious depression.\nOutput:" }, { "from": "gpt", "value": "strengthener" } ]
[ { "from": "human", "value": "Detailed Instructions: 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.\nQ: Title: Trash into Treasure. Sentence 1: I wanted to do something meaningful about an overflowing city dump. Sentence 2: The random trash tossed together inspired me to create salvage art. Sentence 3: I made sculptures from car parts, machinery, and hardware. Sentence 4: I began selling them and teaching art classes to raise awareness.\nA:" }, { "from": "gpt", "value": "Eventually, I helped turn trash into a creative reuse trend." } ]
[ { "from": "human", "value": "In this task, you are given a short passage that conveys stereotype or anti-stereotype about a specific target. A stereotype is an over-generalized belief about a particular group of people. An anti-stereotype is an idea that goes against a common stereotype. You are expected to classify the passage into four types of stereotype or anti-stereotype: gender, profession, race, and religion.\n\nInput: Consider Input: Passage: chess player practices the game always thinking a few moves ahead\n\nOutput: Profession\n\n\nInput: Consider Input: Passage: Persian people have great things they get it fast\n\nOutput: Race\n\n\nInput: Consider Input: Passage: Today in class we learned about Eriteria. It is full of poor people.\n\n" }, { "from": "gpt", "value": "Output: Race\n\n\n" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Predict the next word given an incomplete English Sentence.\n\nbordered with wild rose bushes it's no wonder matthew and marilla are both a little odd living away back here by themselves trees aren't much company though dear knows if they were there'd be enough of them i'd ruther\n" }, { "from": "gpt", "value": "look" } ]
[ { "from": "human", "value": "Instructions: In this task you are given a tweet that contains some form of irony. You must classify the type of irony the tweet has. Label the tweets (\"polarity\",\"situational\",\"other\") based on the irony they have. Situational irony happens when a situation fails to meet some expectations, Label these instances as \"situational\". polarity irony happens when irony is achieved by inverting the intended sentence, Label these instances as \"polarity\". There are other kinds of ironies that are neither polarity nor situational, Label these instances as \"other\". Note that URLs in the text have been replaced with [Link].\nInput: @ the hospital for a new allergy test... Love it.\nOutput:" }, { "from": "gpt", "value": "polarity" } ]
[ { "from": "human", "value": "In 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.\n\nLet me give you an example: Beginning: Butch had a really old computer. Middle 1: Butch decided to order a new computer online. Middle 2: Butch noticed that a storm was approaching to his town. Ending: It arrived and Butch was much happier.\nThe answer to this example can be: 2\nHere is why: People generally don't feel happy about natural disasters like storms. Therefore, we choose 2 in this case.\n\nOK. solve this:\nBeginning: John loves to eat at buffets. Middle 1: John's favorite buffet went out of business. Middle 2: John's favorite buffet was still in business. Ending: John was sad to hear the news.\nAnswer:" }, { "from": "gpt", "value": "2" } ]
[ { "from": "human", "value": "Teacher: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.\nTeacher: Now, understand the problem? Solve this instance: 16, 18, ['3807', '721', 'I', '4933', 'e', 'E', '375', 'w', '3201', 'Y', '7521', 'i', '3283', '5911', '2983', 'f', '8985', '6973', 'H']\nStudent:" }, { "from": "gpt", "value": "37965898f" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a question, along with a context passage which has extra information available on certain terms mentioned in it, i.e., the proper nouns in the passage. Your job is to determine whether information from more than one term is needed to answer the question. Indicate your choice as `a` for Yes or `b` for No.\nQ: Question: How many years long was the period in which copper mineralization and pipe formation occurred? Passage:The copper ore deposits are those of a typical copper porphyry and associated alteration-mineralization. These altered zones include chalcopyrite, pyrite, bornite and molybdenite as hypogene minerals and chalcocite as a supergene mineral. The ore body surrounds the Braden Pipe in a continuous ring with a width of 2000 feet. The pipe is a geologic structure in the shape of an inverted cone, having a surface diameter of 4000 feet, and consisting of post-pipe breccia called the Braden Formation. The boundary of the pipe is marked by this post-pipe breccia and a pre-pipe breccia forming a belt up to 200 feet wide. \"The Braden Pipe was a center of strong mineralization and structural weakness before the pipe was formed.\" Copper mineralization and pipe formation occurred in the Pliocene. Ore was originally mined from the Fortuna orebody at the southwest quadrant starting in 1906. Since 1922, the larger Teniente orebody has also been mined on the east side. \"The best grade of ore is found in altered andesite or in andesitic flow breccia adjacent to the pre-pipe breccia.\"\n\nA:" }, { "from": "gpt", "value": "b" } ]
[ { "from": "human", "value": "Given a sentence in English language, translate the sentence to Tagalog language keeping the meaning of the original sentence intact.\nQ: English sentence: It was, in fact, the only weapon for centuries.In a strange way the bow and crossbow got to the ancient Australians. There learned of the existence of a bow in the 19th century.And since the beginning of the 20th Archer became an athlete, because there were competitions of this shooting.And if you're not an archer, but would like to practice, there is \"Archery\" online.\nA: " }, { "from": "gpt", "value": "Ito ay, sa katunayan, ang tanging armas para sa siglo.Sa isang kakaibang paraan ang bow at pana nakuha sa sinaunang mga Australyano. May natutunan ng pagkakaroon ng isang bow sa ika-19 na siglo.At dahil sa simula ng ika-20 Archer naging isang atleta, dahil may kumpetisyon ng shooting ito.At kung hindi ka isang mamamana, ngunit nais upang magsagawa ng, \"Archery\" online." } ]
[ { "from": "human", "value": "Definition: In this task, you are given a context paragraph, a question based on that and corresponding answer of a question. Your task is to generate supporting fact/knowledge from context paragraph which helps in answering a given question.\nInput: Richard Crealy (born 18 September 1944) is an Australian former tennis player most notable for reaching the finals of the Australian Open in 1970, being a member of the 1970 Australian Davis Cup Team, and winning four Grand Slam titles in doubles. Question: Dick Crealy and Peng Shuai, have which occupation in common? Answer: tennis player\nOutput:" }, { "from": "gpt", "value": "Richard Crealy born 18 September 1944 is an Australian former tennis player most notable for reaching the finals of the Australian Open in 1970, being a member of the 1970 Australian Davis Cup Team, and winning four Grand Slam titles in doubles." } ]
[ { "from": "human", "value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to write a single word that describes the genre that the two sentences belong to, such as face-to-face, government, letters, 9/11, slate, telephone, travel, verbatim, oup, fiction.\n\nInput: Consider Input: Sentence 1: Of course, the extreme in men's dress is the dinner jacket. Sentence 2: Men can wear dinner jackets to dress up.\n\nOutput: slate\n\n\nInput: Consider Input: Sentence 1: The mindwalkers don't just show you something or speak to you, said Thorn. Sentence 2: Thorn said the mindwalkers don't just show you something or speak to you about battles.\n\nOutput: fiction\n\n\nInput: Consider Input: Sentence 1: And it gives a package of free collectibles to any Webmaster who picks up its banner. Sentence 2: It makes the Webmaster pay for the package.\n\n" }, { "from": "gpt", "value": "Output: slate\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: A question is presented to you in this task, and your job is to write a potentially correct answer.\nQ: what team does lamar odom play for 2013?\nA:" }, { "from": "gpt", "value": "Los Angeles Clippers" } ]
[ { "from": "human", "value": "You are given a sentence from a conversation between a human and a virtual assistant. Your task is to classify the sentence into one of the following five action categories - INFORM, INFORM_INTENT, OFFER, REQUEST, REQUEST_ALTS. If the sentence is about informing something, generate 'INFORM'. If it is about requesting something, generate 'REQUEST'. If the sentence mentions requesting an alternative option than the one provided, generate 'REQUEST_ALTS'. Similarly, generate 'OFFER' if the sentence is offering some information. If the sentence is about showing intent to do something, generate 'INFORM_INTENT'.\n\nWe also have Dodgers vs Diamondbacks coming up at Dodger Stadium.\nOFFER\n\nWhich city would you like me to search in, and what kind of events do you like?\nREQUEST\n\nWhat else can you show me.\n" }, { "from": "gpt", "value": "REQUEST_ALTS\n\n" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nGiven a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word '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. 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'. Actions and commands do not have quotations in the input and output.\nExample: jump left\nOutput: I_TURN_LEFT I_JUMP\nThe agent must first turn left and then jump in order to jump to the left.\n\nNew input case for you: walk right thrice and jump left thrice\nOutput:" }, { "from": "gpt", "value": "I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP" } ]
[ { "from": "human", "value": "In this task, based on the given context word, you are asked to create a pair of sentences each containing a blank (_) and their corresponding answer. The sentence pair should look similar, and should be about two related but different objects; for example \"trophy\" and \"suitcase\". Additionally, the two sentences must be different in terms of trigger words (e.g., \"small\" and \"big\") which express contrasting properties about the two objects. The answer must not be associated with the trigger word; instead, it should depend on the context present in twin sentences. Also, the answers should not be ambiguous. For each sentence, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals and proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style or phrase in twin sentences. E.g., a contrasting sentence can always be created using simple negation i.e. by adding not, never, etc. Instead, try to increase diversity. Both twin sentences must contain at least 15 and at most 30 words. Twin sentences must have at least 70% overlapping words. You must utilize the given context word while writing the twin sentences. Each of the twin sentences must contain only one blank. Make sure that ObjectX and Y have the same number e.g. when ObjectX is singular, ObjectY must be singular, too. The two objects (ObjectX & ObjectY) should be used ONCE in each sentence. Here is a list of contrastive words that may be used as trigger words. You should create more such trigger words and use them in your twin sentences.\n\| Attribute \| triggerword \| contrastive triggerword \| \n\| age \| old \| new \| \n\| altitude \| low \| high \|\n\| area \| small \| vast \| \n\| brightness \| dark \| light \| \n\| clarity \| obscure \| clear \| \n\| cleanness \| dirty \| clean \| \n\| complexity \| simple \| complex \| \n\| cost \| cheap \| expensive \|\n\| density \| sparse \| dense \|\n\| depth \| shallow \| deep \|\n\| distance \| near \| far \| \n\| electric conductivity \| low \| high \|\n\| flexibility \| rigid \| flexible \|\n\| granularity \| fine \| coarse \| \n\| hardness \| soft \| hard \| \n\| length \| short \| long \| \n\| magnitude \| small \| large \| \n\| mass \| small \| large \| \n\| odor \| weak \| strong \| \n\| pressure \| low \| high \| \n\| resistance \| low \| high \| \n\| shape \| round \| sharp \|\n\| shape \| flat \| spiky \|\n\| size \| small \| large \| \n\| sound \| quiet \| loud \| \n\| sound pitch \| low \| high \| \n\| speed \| slow \| fast \| \n\| stability \| unstable \| stable \| \n\| strength \| weak \| strong \| \n\| temperature \| low \| high \| \n\| texture \| smooth \| rough \| \n\| thermal conductivity \| low \| high \|\n\| thickness \| thin \| thick \| \n\| volume \| small \| large \|\n\| weight \| light \| heavy \| \n\| width \| narrow \| wide \| \n\| location \| in \| out \|\n\| location \| up \| down \|\n\| location \| above \| below \|\n\| location \| on \| off \|\n\| location \| to \| from \|\n\n\nContext Word: clothe.\nSentence 1: James could not get the bag closed because of the clothe in it. The _ is plenty. \nAnswer1: cloth. \nSentence 2: James could not get the bag closed because of the clothe in it. The _ is small. \nAnswer2: bag.\n\nContext Word: paintings.\nSentence 1: The man chose the watercolor for his paintings rather than the acrylic because the _ was ugly. \nAnswer1: acrylic. \nSentence 2: The man chose the watercolor for his paintings rather than the acrylic because the _ was attractive. \nAnswer2: watercolor.\n\nContext Word: coronary artery disease.\n" }, { "from": "gpt", "value": "Sentence 1: Because Steve had coronary artery disease, he chose vegetables over potato chips because eating the _ is worse for his disease. \nAnswer1: potato chips. \nSentence 2: Because Steve had coronary artery disease, he chose vegetables over potato chips because eating the _ is better for his disease. \nAnswer2: vegetables.\n\n" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given two lists A,B. Find the longest common subsequence in the lists A and B.\nTeacher: Now, understand the problem? Solve this instance: ['l', 'f', 1593, '1537', '407', '9101', '589', 'u', '7817', '9261', 'L', '961', 'O', 419], [2067, 963, 'A', 'J', 'd', 'L', 'j', 5423, 'P', '1537', '407', '9101', '589', 'u', '7817', '9261', 'L', '961', 'D', 'G', 6171, 'L', 'a', 'S', 5065]\nStudent:" }, { "from": "gpt", "value": "1537, 407, 9101, 589, u, 7817, 9261, L, 961" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given the beginning and the middle of a three-part story. Your job is to complete the short story by writing a probable ending. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the ending, and use names instead of pronouns (e.g. he / she) wherever possible.\nQ: Beginning: Lola was driving home. Middle: Lola got a flat tire and a stranger help her.\nA:" }, { "from": "gpt", "value": "She was happy for the help." } ]
[ { "from": "human", "value": "In this task, you will be presented with a question and you have to answer the question based on your knowledge. Your answers should be as short as possible.\nOne example is below.\nQ: Who were the builders of the mosque in Herat with fire temples ?\nA: Ghurids\nRationale: This is a good example. Ghurids were the builders of the mosque in Herat with fire temples.\nQ: In what year was the feminist born ?\nA:" }, { "from": "gpt", "value": "1944" } ]
[ { "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: toxic and non-toxic. Toxicity is defiend as anything that is rude, disrespectful, or unreasonable that would make someone want to leave a converation.\n\nExample input: Comment: i am just sorry that khadr didnt get a bullet in the head before he blew the head off that innocent father because his islamic boogie skywizard told him to.\nExample output: Toxic\nExample explanation: This is a toxic comment because it advocates acts of violence.\nQ: Comment: So if the state oil subsidy structure is so flawed why the heck are we electing oil guys to the legislature? Stupid is as stupid does.\nA:" }, { "from": "gpt", "value": "Toxic" } ]
[ { "from": "human", "value": "The task is to generate text based off 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 intent behind doing the event, i.e. why did the person do that action.\n\nInput: Consider Input: PersonX makes PersonY image\n\nOutput: to try out photoshop\n\n\nInput: Consider Input: PersonX separates from PersonX's husband\n\nOutput: to be alone\n\n\nInput: Consider Input: PersonX gets home from school\n\n" }, { "from": "gpt", "value": "Output: to rest\n\n\n" } ]
[ { "from": "human", "value": "In this task, you're given a context, a sentence, and a character. The sentence describes an action or job of the given character. Also, the context provides more information about the sentence or the character. Your task is to return one of the emotions which are expressed by the Character in the given sentence. For that you can use the Context; however, Context is not provided in all the inputs. Also, in some inputs, there can be zero emotion; for that return 'None'.\nOne example is below.\nQ: Context: A cook was carrying an armful of oranged in the kitchen. \n Sentence: He dropped one on the floor by accident. \n Character: Cook\nA: annoyed\nRationale: The cook dropped one orange on the floor, so, he must feel annoyed at that time.\nQ: Context: Brandy liked to walk in the park. One day in the park, Brandy found some money. She was perplexed as to what to do with the money. She eventually turned it into the Police. \n Sentence: She never regretted her decision. \n Character: Brandy\nA:" }, { "from": "gpt", "value": "helpful" } ]
[ { "from": "human", "value": "In this task, answer 'Yes' if the frequency of the given word in the two sentences is equal, else answer 'No'.\nQ: Sentence1: 'a red bench sitting underneath a widow against wall', Sentence2: 'a clock tower stands next to a building above a forest'. Is the frequency of the word 'a' in two sentences equal?\nA: " }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given a positive review and your task is to convert it to a negative review by making minimal changes. Avoid changing the context of the review.\nTeacher: Now, understand the problem? Solve this instance: i have had a great experience every time from start to finish .\nStudent:" }, { "from": "gpt", "value": "i have had a bad experience every time from start to finish ." } ]
[ { "from": "human", "value": "Teacher:From the given sentence, extract the phrase (often noun or verb) that carries the given relationship. The generated phrase should be present in the sentence.\nTeacher: Now, understand the problem? Solve this instance: Given Relationship: 'spread in', Sentence: 'They were introduced to China as Buddhism spread to China .'\nStudent:" }, { "from": "gpt", "value": "spread" } ]
[ { "from": "human", "value": "In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to provide one question which clarifies the input question and it has one unique answer, and also provide an answer to the generated question. Generated question and answer should be separated with a new line.\n\nExample Input: How many big 12 championships does ou have?\nExample Output: How many big 12 championships does ou have as of 2017? \n 11\n\nExample Input: When does the my little pony movie release?\nExample Output: When does the My Little Pony: The Movie (1986 film) release? \n June 6, 1986\n\nExample Input: When did the us leave the vietnam war?\nExample Output:" }, { "from": "gpt", "value": "When did the us troop presence in Vietnam peak during the vietnam war? \n 1968\n\n" } ]
[ { "from": "human", "value": "In this task you are given a sentence pair from wikipedia that have high lexical overlap. If the sentences have the same meaning and are just paraphrases of each other label them as \"Paraphrase\" , if not label them as \"Not paraphrase\". The two sentences are seperated by a new line.\nQ: It has been awarded to civilian medical staff , Qantas crews , military personnel and embassy personnel .\nIt has been awarded to civilian medical personnel , Qantas crews , military personnel , and Embassy staff .\nA: " }, { "from": "gpt", "value": "Paraphrase" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you need to replace a letter in the sentence with another given letter.\nProblem:Sentence: 'a tray topped with a micheal jackson hat and matching glove'. Replace the letter 'e' with 'f' in the sentence.\nSolution:" }, { "from": "gpt", "value": "a tray toppfd with a michfal jackson hat and matching glovf" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a statement, the genre to which that statement belongs, and a label indicating if the statement should be agreed with (entailment), disagreed with (contradiction), or neither (neutral). Your job is to write a sentence that describes the genre that follows the tone with respect to the statement, as indicated by the label. If sentence X agrees with sentence Y, the can be concluded from one another. If sentence X disagrees with sentence Y, they can not be correct at the same time. The sentence must also belong to the genre specified.\nProblem:Statement: No, but it is always well to learn new ways.\nLabel: neutral.\nGenre: fiction.\nSolution:" }, { "from": "gpt", "value": "New ways to do things will expand your horizons." } ]
[ { "from": "human", "value": "In this task, you are given a text from tweets. Your task is to classify given tweet text into two categories: 1) positive, and 2) negative based on its content.\n\nLet me give you an example: @justinchuan Awww! I was thinking about you lot up there! Glad you enjoyed it\nThe answer to this example can be: positive\nHere is why: There is an expression of happiness in this tweet text, hence we can say it's positive.\n\nOK. solve this:\n@UCYIMD1 I called u last nite... No answer \nAnswer:" }, { "from": "gpt", "value": "negative" } ]
[ { "from": "human", "value": "In this task, you need to replace a letter in the sentence with another given letter.\nOne example is below.\nQ: Sentence: 'group of motorcycle motorists trying to merge into traffic'. Replace the letter 'o' with 'n' in the sentence.\nA: grnup nf mntnrcycle mntnrists trying tn merge intn traffic\nRationale: The letter 'o' has been replaced in the letter 'n'.\nQ: Sentence: 'man in a suit talks on his cell phone while riding a bike down the street'. Replace the letter 'o' with 'j' in the sentence.\nA:" }, { "from": "gpt", "value": "man in a suit talks jn his cell phjne while riding a bike djwn the street" } ]
[ { "from": "human", "value": "instruction:\nIn this task, you are given a question, and your task is to predict the context of the question. We assume that someone named X asked the question from Y. The context of the question means the previous situation that led X to ask this question.\nquestion:\nDo you live in this city?\nanswer:\nX and Y are colleagues who are leaving work on a Friday at the same time.\n\n\nquestion:\nDo you like going for walks?\nanswer:\nX wants to know what activities Y likes to do during weekends.\n\n\nquestion:\nAre you happy working here at this job?\nanswer:\n" }, { "from": "gpt", "value": "X and Y are colleagues who are leaving work on a Friday at the same time.\n\n\n" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given one English sentence. The major part of the sentences talk about health-related topics, but some of the them describe an organization and its activities. Your job is to translate the given sentences into Swedish.\nTeacher: Now, understand the problem? Solve this instance: TU:\nStudent:" }, { "from": "gpt", "value": "TU:" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, you're given five sentences, numbered 1 through 5, and two options a and b for possible titles for the story. Your job is to choose the title that better fits the story. Indicate your choice by 'a' or 'b'.\nPROBLEM: Sentence 1: A guy on my favorite forum uses pictures of Pusheen. Sentence 2: He responds to everything with it. Sentence 3: He makes people laugh with his pusheen gifts. Sentence 4: He posts red pandas also. Sentence 5: He became beloved in the community. Choices: a. Flipped. b. Pusheen.\n\nSOLUTION: b\n\nPROBLEM: Sentence 1: Joyce silently sat savoring a piece of chocolate candy in her closet. Sentence 2: There was a knock on the locked door. Sentence 3: Joyce didn't dare make a sound. Sentence 4: Soon little footsteps walked out of the room. Sentence 5: Joyce would have to return to being the mom, but not just yet. Choices: a. All About a Boy. b. Peace and Quiet.\n\nSOLUTION: b\n\nPROBLEM: Sentence 1: Karl was sick with a flu. Sentence 2: He was prescribed some pills for the symptoms. Sentence 3: Unfortunately Karl took the wrong ones. Sentence 4: He felt even worse. Sentence 5: Karl had to go to the hospital over it. Choices: a. Wrong Medicine. b. Taking Selfies.\n\nSOLUTION:" }, { "from": "gpt", "value": "a\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given an input stream, and your task is to produce a grammatically correct version of the input sentence. 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 grammatically correct version of the input stream. Stream words are in [] and have been separated with a comma. The sentence can contain words that have case, punctuation, stem-based, intra-word, and digit punctuation errors that need to be corrected. For example, the text should be uppercased/lowercased as per necessity (like the beginning of a sentence, proper nouns, etc.), and digits need to be normalized (6 as six and so on). Note that you don't need to normalize the years. You don't need to fully edit the sentences, if end of the input stream contains sentence fragments, keep them as is.\nQ: ['so', 'I', 'never', 'looked', 'at', 'extracurriculars', 'as', 'a', 'way', 'to', 'get', 'into', 'college', 'because', 'that', 'was', 'not', 'my', 'purpose', 'of', 'doing', 'them', 'at', 'all', 'I', 'actually', \"didn't\", 'like', 'when', 'people', 'said', 'oh', 'you', 'should', 'do', 'a', 'lot', 'to', 'get', 'into', 'college', 'I', 'always', 'looked', 'at', 'it', 'as', 'like', 'what', 'did', 'I', 'like', 'to', '', 'do', 'what', 'do', 'I', 'love', 'to', 'do', 'and', \"I'm\", 'going', 'to', 'do', 'it', 'to', 'the', 'best', 'and', \"that's\", 'how', 'I', 'always', 'looked', 'at', 'extracurriculars', 'so', 'I', 'got', 'involved', 'in', 'so', 'many', 'things', 'because', 'of', 'that', 'not', 'to', 'get', 'into', 'college', 'I', 'was', 'in', 'journalism', 'I', 'loved']\nA:" }, { "from": "gpt", "value": "['so', 'I', 'never', 'looked', 'at', 'extracurriculars', 'as', 'a', 'way', 'to', 'get', 'into', 'college', \"'cause\", 'that', 'was', 'not', 'my', 'purpose', 'of', 'doing', 'them', 'at', 'all.', 'I', 'actually', \"didn't\", 'like', 'when', 'people', 'said,', '\"Oh,', 'you', 'should', 'do', 'a', 'lot', 'to', 'get', 'into', 'college.\"', 'I', 'always', 'looked', 'at', 'it', 'as', 'like', 'what', 'did', 'I', 'like', 'to', '', 'do', 'what', 'do', 'I', 'love', 'to', 'do,', 'and', \"I'm\", 'going', 'to', 'do', 'it', 'to', 'the', 'best,', 'and', \"that's\", 'how', 'I', 'always', 'looked', 'at', 'extracurriculars,', 'so', 'I', 'got', 'involved', 'in', 'so', 'many', 'things', 'because', 'of', 'that,', 'not', 'to', 'get', 'into', 'college.', 'I', 'was', 'in', 'journalism,', 'I', 'loved']" } ]
[ { "from": "human", "value": "Teacher:An answer is given. Generate a question for which the given answer is either a direct or partial answer.\nTeacher: Now, understand the problem? Solve this instance: Answer: david perdue\nStudent:" }, { "from": "gpt", "value": "what are georgias state senators?" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, based on the given context word, you are asked to create a pair of sentences each containing a blank (_). The sentence pair should look similar and should be about two different persons (PersonX and PersonY). Additionally, the two sentences must be different in terms of trigger words (e.g., \"sympathetic\" and \"stern\") which express contrasting attributes about the two persons. The answer to the first and the second sentence must be PersonX and PersonY, respectively. PersonX and PersonY should not be equally likely to fill the blank. For each sentence, there should be an agreed upon 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 (e.g., Donald Trump, Putin, etc.) in your sentences. Avoid repeating the same style or phrase in twin sentences e.g., a contrasting sentence can always be created using simple negation i.e. by adding not, never, etc. Instead, try to increase diversity. Both twin sentences must contain at least 15 and at most 30 words. Twin sentences must have at least 70% overlapping words. You must utilize the given context word while writing the twin sentences. Each of the twin sentences must contain only one blank. Make sure that PersonX and PersonY have the same gender. In each sentence, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY.\n\nContext Word: Hawaii.\n" }, { "from": "gpt", "value": "Sentence 1: PersonX was very excited to be flying to Hawaii with PersonY who has flown many times before, but _ was feeling anxious. \nSentence 2: PersonX was very excited to be flying to Hawaii with PersonY who has flown many times before, but _ was feeling calm." } ]
[ { "from": "human", "value": "In this task, you are given sentences from movie reviews. The task is to classify a sentence as \"POS\" if the sentiment of the sentence is positive or as \"NEG\" if the sentiment of the sentence is negative\nExample: It 's a lovely film with lovely performances by Buy and Accorsi .\nExample solution: POS\nExample explanation: The sentiment of the sentence is positive. Hence, the label is 'POS'.\n\nProblem: As violent , profane and exploitative as the most offensive action flick you 've ever seen .\n" }, { "from": "gpt", "value": "Solution: NEG" } ]
[ { "from": "human", "value": "Instructions: In this task, you're given two sentences, sentence 1 and sentence 2, and the genre they belong to. Your job is to determine if the two sentences belong to the same genre or not. Indicate your answer with Y and N respectively. Genres available include: face-to-face, government, letters, 9/11, slate, telephone, travel, verbatim, oup, fiction. Sentences belonging to 'face-to-face' genres relate to conversations or dialogues, 'government' encompasses information released from public government websites, 'letters' refers to any written work for philanthropic fundraising, '9/11' relates to information pertaining to the 9/11 attacks, 'oup' includes non-fiction works on the textile industry and child development, 'slate' refers to any cultural topic that appears in the slate magazine, 'telephone' includes telephonic dialogue, 'travel' deals with information in travel guides, 'verbatim' includes short posts regarding linguistics, and 'fiction' includes popular works of fiction like 'The Secret Adversary' etc.\nInput: Sentence 1: But until then, you'll have to carry the con.' Sentence 2: You have to carry the scam. Genre: fiction.\nOutput:" }, { "from": "gpt", "value": "Y" } ]
[ { "from": "human", "value": "Instructions: You are given a sentence and a question in the input. If the information provided in the sentence is enough to answer the question, label \"Yes\", otherwise label \"No\". Do not use any facts other than those provided in the sentence while labeling \"Yes\" or \"No\". There are only two types of valid responses: Yes and No.\nInput: Sentence: Lauren gives Lulu her lamb to sleep with. \nQuestion: What do Lauren and Alan give to Lulu to sleep with?\nOutput:" }, { "from": "gpt", "value": "Yes." } ]
[ { "from": "human", "value": "In this task, you are given triplets. Each triplet is in the form of [subject, predicate, object]. Your task is to generate proper sentence that utilizes these triples. The objective is to construct a sentence that (a) captures the facts specified in the triples and (b) is a well-formed sentence easily understandable by a human. All triple values need not be used directly in the sentence as long as the facts are adequately captured.\n\nLet me give you an example: [['Northwestern College', 'NICKNAME', 'Red Raiders'], ['Northwestern College', 'LOCATION', 'Orange City, Iowa']]\nThe answer to this example can be: The team whose nickname is red raiders is located in the orange city, iowa\nHere is why: This sentence uses the triplets by correctly using the (subject, predicate, object) semantics for both the triplets provided. Since college teams are popularly associated with nicknames, some information in the generated sentence can be inferred. In this case, Northwestern College was replaced with the team automatically.\n\nOK. solve this:\n[['Pierce County, Washington', 'LARGEST_CITY', 'Tacoma, Washington']]\nAnswer:" }, { "from": "gpt", "value": "Pierce County is the largest city in Tacoma, Washington." } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, we ask you to elaborate the sentence without changing its general meaning. You can do so by explaining further the input sentence, using more precise wording, adding qualifiers and auxiliary information etc.\nSee one example below:\nProblem: The Inheritance Cycle is a series of fantasy books written by Christopher Paolini.\nSolution: The Inheritance Cycle is a tetralogy of young adult high fantasy novels written by American author Christopher Paolini.\nExplanation: The output sentence elaborates on the input sentence without changing its general meaning e.g. \"tetralogy of young adult high fantasy novels\".\n\nProblem: In marine sediments methane is produced when sulfates are low .\nSolution:" }, { "from": "gpt", "value": "In marine sediments the biological production of methane , also termed methanogenesis , is generally confined to where sulfates are depleted , below the top layers ." } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you need to answer the given multiple-choice question on the general math. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.\nExample: Problem: what is difference between biggest and smallest fraction among 2 / 3 , 3 / 4 , 4 / 5 and 5 / 3 \nOptions: a ) 2 / 5 , b ) 3 / 5 , c ) 1 / 6 , d ) 1 , e ) none of these\nOutput: d\n\"explanation : 2 / 3 = . 66 , 3 / 4 = . 75 , 4 / 5 = . 8 and 5 / 3 = 1.66 so the biggest is 5 / 3 and the smallest is 2 / 3 their difference is 5 / 3 - 2 / 3 = 3 / 3 = 1 option d\"\n\nNew input case for you: Problem: sam wrote 7 letters on tuesday and 3 letters on wednesday . how many letters did he write on average per day ? \nOptions: a ) 10 , b ) 4 , c ) 21 , d ) 3 , e ) 5\nOutput:" }, { "from": "gpt", "value": "e" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given an ambiguous question/query (which can be answered in more than one way) and a clarification statement to understand the query more precisely. Your task to classify that if the given clarification accurately clarifies the given query or not and based on that provide 'Yes' or 'No'.\nTeacher: Now, understand the problem? Solve this instance: Query: map \n Clarification: are you looking for the nearest junck yard\nStudent:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a hateful post in English from online platforms. You are expected to classify the target being harassed in the post as individual or generic, i.e., single person or a group of people. Note that the URLs in the text have been replaced with [Link].\nQ: Post: get u a girl with a resting bitch face that only smiles at u\nA:" }, { "from": "gpt", "value": "Generic" } ]
[ { "from": "human", "value": "Q: 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\".\nProcess: -Magma rises from deep in the earth -The magma goes into volcanos -The volcanos pressure the magma upwards -The pressure causes the magma to push through the surface of the volcano -The lava cools -The lava forms new rock -New magma is pressured to the surface of the volcano -The volcano bursts through the rock the formed after the last eruption.\n Question: What is the effect of a winter storm covers a mountain with blizzard snow on magma stays cool inside of a volcano after a winter storm.?\nA:" }, { "from": "gpt", "value": "for" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGiven a real-life anecdote of a complex ethical situation, generate a suitable title that describes the main event/root cause of the situation. Imagine that the given text is a social media post, and you have to write the title of the post, so the users can decide to read the main text or not.\n\nSo I know this is going to sound like a SHP, and I know many are going to call it that anyway, but this is really my life. From a young age I have always been freakishly tall. I was 6'0 at 14. I am now bordering on 7 feet at 22. My growth has slowed down considerably, which I am thankful for, but throughout my life I have been struggling.\n\nI know a lot of guys want to be taller. In reality, you feel very strange around your friends when you're growing up, and your family photos when you're a child make you look like a monster with a childs face and a mans body. I am also very shy despite what people think and I was verbally bullied at times based on my height and lankiness in highschool. I have to eat a lot of food to put on weight. I eat almost 4,000 calories a day to maintain my average build.\n\nNow I have started working out to increase my self esteem and I eat almost 5,000 a day. I weigh 320 pounds more or less. I can't go on many rides at theme parks and there are many activities I miss out on. Driving is terrible unless im in a larger pick up truck with cab space, which is very expensive. I don't have too many friends.\n\nWomen are also intimidated by me. I have a nice face on my profile but when we meet up they are very taken aback and quiet. They don't enjoy being around me. That all changed when I met my girlfriend who is 5'10, but has been amazing to me.\n\nWe have been dating for almost a year and have only been able to penetrate her a few times. My penis is too big for her she says. I measured it at fully erect and I am bordering on nine inches when hard, a little less. The thickness is also an issue since I can only get myself \"in\" maybe an inch or two before she starts complaining.\n\nWe have settled into her giving me oral sex, which I do enjoy somewhat and but that she REALLY enjoys. She is very enthusiastic to put it mildly, and she also expects me to be as enthusiastic when I give her oral sex which I also dont like that much but I do it to make her happy.\n\nHowever as a man I have a deep desire to penetrate a woman, its just a natural feeling. And whenever I sort of lead things that way she rejects me. She has allowed me to rub against her and other things but thats it. \n\nNow everything has gone to a head and she has flat out told me that she does not want me to fuck her, and I am very angry and hurt. I realize that I am not a \"normal\" man and I don't want to hurt her, but I don't know if I can keep living like this and be happy. I don't enjoy blowjobs nearly as much as she does. I don't enjoy handjobs at all, I don't like rubbing against her vagina as its not the same and sort of emasculating.\n\ni also know that she has been penetrated by her smaller boyfriends, but she wont allow me due to my size, which also hurts.\n\nI still think there are other options for us to maybe try penetration, but i am angry that she has shut the door entirely. I am almost thinking about breaking up and trying to find someone else but i do love her.\n\nAITA for being angry that my gf wont try penetrative sex?\nOutput:" }, { "from": "gpt", "value": "being angry at my gf for not wanting to have penetrative sex with me" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you need to output 'Yes' if the given number is a prime number otherwise output 'No'. A 'prime number' is a a whole number above 1 that can not be made by multiplying other whole numbers.\nPart 2. Example\n7\nAnswer: Yes\nExplanation: 7 is a prime number as it has no factors greater than 1. So, it can't be made by multiplying other whole numbers and the answer is 'Yes'.\nPart 3. Exercise\n93795\nAnswer:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "Q: In 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 coherent / plausible by writing \"1\" or \"2\" in the output. If both sentences are plausible, pick the one that makes most sense.\nBeginning: Amy and Charles were going shopping for an engagement ring. Middle 1: Amy got a ring she loved. Middle 2: Amy got a rhino that she loved. Ending: Amy started at her new ring all the way home.\nA:" }, { "from": "gpt", "value": "1" } ]
[ { "from": "human", "value": "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.\nQ: Abigail entered the attic. Jackson entered the attic. The strawberry is in the green_bottle. Jackson exited the attic. Abigail moved the strawberry to the green_drawer. Where will Jackson look for the strawberry? Evelyn entered the crawlspace. Abigail entered the crawlspace. The tangerine is in the blue_cupboard. Abigail exited the crawlspace. Evelyn moved the tangerine to the green_crate. Evelyn exited the crawlspace. Abigail entered the crawlspace. Where is the tangerine really?\nA: " }, { "from": "gpt", "value": "green_crate" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. If the conversation begins with a question, label it '1' otherwise '0'.\n\n Person1: Shall we have some soup first ? \n Person2: No , thank you . I don't like soup . I'd rather have some fruit juice to start with . \n Person1: Ok , and what about the main course ? Which would you rather have fish or meat ? \n Person2: Meat , I think . \n Person1: Don't you like fish then ? \n Person2: I do , but I want meat . \n Person1: Shall we have some white wine then ? \n Person2: Yes , but I prefer red wine with meat . \n Person1: What would you like for dessert ? \n Person2: I just want to have a coffee , I think . \n Person1: Fine , and after dinner , shall we go to a disco ? \n Person2: No , thanks . I'd like to go straight home . I'm very tired . \n" }, { "from": "gpt", "value": "0" } ]
[ { "from": "human", "value": "instruction:\nYou are supposed to identify the category of a high-school level math question. There are five possible categories (1) algebra (2) arithmetic (3) measurement (4) numbers, and (5) probability. Use the following guidelines: (1) 'algebra' questions will typically contain letter variables and will ask you to find the value of a variable (2) 'arithmetic' questions will ask the sum, difference, multiplication, division, power, square root or value of expressions involving brackets (3) 'measurement' questions are questions that ask to convert a quantity from some unit to some other unit (4) 'numbers' questions will be about bases, remainders, divisors, GCD, LCM etc. (5) 'probability' questions will ask about the probability of the occurrence of something. A question must belong to only one category.\nquestion:\nWhat is prob of sequence vc when two letters picked without replacement from zqjzzvvzozqvcq?\nanswer:\nprobability\n\n\nquestion:\nWhat is 3641 to the power of 1/2, to the nearest integer?\nanswer:\narithmetic\n\n\nquestion:\nSuppose 0 = t - 3j + j - 8, -4 = t - 5j. What is the highest common divisor of t and 16?\nanswer:\n" }, { "from": "gpt", "value": "numbers\n\n\n" } ]
[ { "from": "human", "value": "Q: In this task, you are given a text from tweets. Your task is to classify given tweet text into two categories: 1) positive, and 2) negative based on its content.\n@UCYIMD1 I called u last nite... No answer \nA:" }, { "from": "gpt", "value": "negative" } ]
[ { "from": "human", "value": "Instructions: A ploynomial equation is a sum of terms. Here each term is either a constant number, or consists of the variable x raised to a certain power and multiplied by a number. These numbers are called weights. For example, in the polynomial: 2x^2+3x+4, the weights are: 2,3,4. You can present a polynomial with the list of its weights, for example, equation weights = [6, 4] represent the equation 6x + 4 and equation weights = [1, 3, 4] represent the equation 1x^2 + 3x + 4. In this task, you need to compute the result of a polynomial expression by substituing a given value of x in the given polynomial equation. Equation weights are given as a list.\nInput: x = 10, equation weights = [3, 4, 0]\nOutput:" }, { "from": "gpt", "value": "340" } ]
[ { "from": "human", "value": "In this task, you are given an input stream, and your task is to produce a grammatically correct version of the input sentence. 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 grammatically correct version of the input stream. Stream words are in [] and have been separated with a comma. The sentence can contain words that have case, punctuation, stem-based, intra-word, and digit punctuation errors that need to be corrected. For example, the text should be uppercased/lowercased as per necessity (like the beginning of a sentence, proper nouns, etc.), and digits need to be normalized (6 as six and so on). Note that you don't need to normalize the years. You don't need to fully edit the sentences, if end of the input stream contains sentence fragments, keep them as is.\n\n['simplify', 'the', 'expression', '18x', 'to', 'the', 'fourth', 'minus', '3x', 'squared', 'plus', '6x', 'minus', '4', 'all', 'of', 'that', 'over', 'is', '6x', 'so', \"there's\", 'a', 'couple', 'of', 'ways', 'to', 'think', 'about', 'them', \"they're\", 'all', 'really', 'equivalent', 'you', 'can', 'really', 'just', 'view', 'this', 'up', 'here', 'as', 'being', 'the', 'exact', 'same', 'thing', 'as', '', '18x', 'to', 'the', 'fourth', 'over', '6x', 'plus', 'negative', '3x', 'squared', 'over', '6x', 'or', 'you', 'could', 'say', 'minus', '3x', 'squared', 'over', '6x', 'plus', '6x', 'over', '6x', 'minus', '4', '', 'over', '6x', 'now', \"there's\", 'a', 'couple', 'of', 'ways', 'to', 'think', 'about', 'it', 'one', 'is', 'I', 'just', 'kind', 'of', 'decomposed', 'this', 'numerator', 'up']" }, { "from": "gpt", "value": "['Simplify', 'the', 'expression', '18x', 'to', 'the', 'fourth', 'minus', '3x', 'squared', 'plus', '6x', 'minus', '4,', 'all', 'of', 'that', 'over', 'is', '6x', 'so', \"there's\", 'a', 'couple', 'of', 'ways', 'to', 'think', 'about', 'them', \"they're\", 'all', 'really', 'equivalent', 'you', 'can', 'really', 'just', 'view', 'this', 'up', 'here', 'as', 'being', 'the', 'exact', 'same', 'thing', 'as', '', '18x', 'to', 'the', 'fourth', 'over', '6x', 'plus', 'negative', '3x', 'squared', 'over', '6x', 'or', 'you', 'could', 'say', 'minus', '3x', 'squared', 'over', '6x', 'plus', '6x', 'over', '6x', 'minus', '4', '', 'over', '6x', 'now', \"there's\", 'a', 'couple', 'of', 'ways', 'to', 'think', 'about', 'it', 'one', 'is', 'I', 'just', 'kind', 'of', 'decomposed', 'this', 'numerator', 'up']" } ]
[ { "from": "human", "value": "Q: In this task, you are given a question containing a blank (_) and two options. You should pick the best option to answer the question. Please answer with \"A\" or \"B\".\nSandra tried out a new conditioner for her hair that makes it curly, but was upset with the results because the _ was too straight. (A) conditioner (B) hair\nA:" }, { "from": "gpt", "value": "B" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nYou 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\nSentence: Rob and Rich are doing gymnastics. Rich is dripping wet with sweat and Rob appears to be sweating only a little. Question: Who's doing the more intense exercise? (A) Rob (B) Rich\nOutput:" }, { "from": "gpt", "value": "B" } ]
[ { "from": "human", "value": "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.\n\nInput: Consider Input: password = THan44N7\n\nOutput: 0\n\n\nInput: Consider Input: password = .lDvoyXr!db7NN5M1!A3E.Fy9QiNztXncf\n\nOutput: 14\n\n\nInput: Consider Input: password = aa1GoR7CQ6gYdRU!bVsitGSSh\n\n" }, { "from": "gpt", "value": "Output: 5\n\n\n" } ]
[ { "from": "human", "value": "Definition: You are given a list of queries separated by new line. Your job is to answer with the query that is the most well-formed or well-structured query in terms of grammar, punctuations, or spelling errors.\nInput: Where is oil filter on 2006 trailblazer ?\nScrutiny in a sentence as a noun ?\nHow many grams of fat is in 2 strips of bacon ?\nWhat is the ionic charge for sodium ?\nOutput:" }, { "from": "gpt", "value": "What is the ionic charge for sodium ?" } ]
[ { "from": "human", "value": "In this task, you are given a question and an answer, you would be asked to create the sentence based on the Question-Answer provided. It should be contained within the Question-Answer provided.\n\nExample Input: Question: What kind of system do echinoderms possess? Answer: water-based circulatory\nExample Output: Echinoderms possess a water-based circulatory system.\n\nExample Input: Question: Which action is most likely a learned behavior? Answer: A lion cub practices its hunting skills.\nExample Output: A lion cub practices its hunting skills action is most likely a learned behavior.\n\nExample Input: Question: What happens when forces of evolution work over a long period of time? Answer: macroevolution\nExample Output:" }, { "from": "gpt", "value": "Macroevolution happens when forces of evolution work over a long period of time.\n\n" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nYou are given a question. You need to detect which category better describes the question. A question belongs to the description category if it asks about description and abstract concepts. Entity questions are about entities such as animals, colors, sports, etc. Abbreviation questions ask about abbreviations and expressions abbreviated. Questions regarding human beings, description of a person, and a group or organization of persons are categorized as Human. Quantity questions are asking about numeric values and Location questions ask about locations, cities, and countries. Answer with \"Description\", \"Entity\", \"Abbreviation\", \"Person\", \"Quantity\", and \"Location\".\nExample: What's the most common name in nursery rhymes ?\nOutput: Person\nThis question is about people's names. So, the output should be \"Person\".\n\nNew input case for you: On what river is Strasbourg built ?\nOutput:" }, { "from": "gpt", "value": "Location" } ]
[ { "from": "human", "value": "Q: In this task you will be given a list, of lists, of integers. For every inner list contained in the input list, you should multiply every even number in that list. The output should be a list of integers with the same length as the number of lists in the input list. If there are no even numbers in an inner list you should output 0 for that list.\n[[47, -36, -47, 38], [-3, 41, 35, -4, 12], [-23, 13, 21, -40], [-28, 33], [27, 13, -15, -23], [42, 8, 13], [36, -42, -28, -49], [-1, -5, -17, -48, -1], [-5, 2, 47, -16, 24], [50, -13, 29, 12], [14, 1, -15, 24], [-29, -25], [6, -50, -50, -49], [-49, -44, 21, -33], [-40, 9]]\nA:" }, { "from": "gpt", "value": "[-1368, -48, -40, -28, 0, 336, 42336, -48, -768, 600, 336, 0, 15000, -44, -40]" } ]
[ { "from": "human", "value": "In this task, you are presented with a term, a description of the term, and an expected answer ('yes' or 'no'). You should write a yes-no question about the given term such that the answer is the one provided to you (i.e., If the answer is \"No\", you should ask a question that its answer would be \"No\", and if the answer is \"Yes\", you should ask a question that its answer is \"Yes\". ). The question should have a definitive answer (as opposed to ambiguous or subjective questions, e.g., Is Batman a good movie?). Create a question such that its answer can not be found easily on a single web page (e.g., mentioned in a Wikipedia page). This can be accomplished if answering the question requires more than one fact (facts = statements that can be found on a Wikipedia page or Google). For example, answering the question 'did Aristotle use a laptop?', one needs the know about the invention of the laptop and the death of Aristotle. Avoid questions should not just compare the properties of objects (e.g., Is a door bigger than an elephant?) or those that refer to details in the given description.\n\n[EX Q]: Term: Hotel manager, Description: person managing a hotel, Answer:No\n[EX A]: Could Charlie Bucket be a hotel manager?\n\n[EX Q]: Term: Harry Potter, Description: Fantasy literature series, Answer:Yes\n[EX A]: Was the writer on welfare before Harry Potter was published?\n\n[EX Q]: Term: Guinea pig, Description: domesticated rodent species from South America, Answer:Yes\n[EX A]:" }, { "from": "gpt", "value": "Are Guinea pigs an export of South America?\n\n" } ]
[ { "from": "human", "value": "Given a pair of words, deduce the type of relationship between them. The various types of relations are: 'Entails, HasProperty, Synonym, Antonym, HasA, MemberOf, PartOf, MadeOf, IsA'. Let's denote the first word by X and the second word by Y. An 'IsA' relation holds when 'X is a kind of Y'. An 'Antonym' relation holds when 'X can be used as the opposite of Y'. A 'Synonym' relation applies when 'X can be used in place of Y, without changing the meaning'. A 'PartOf' relation holds when 'X is a part of Y'. A 'MemberOf' relation holds when 'X is a member of Y'. A 'MadeOf' relation holds when 'X is made of Y'. An 'Entailment' relation holds when 'If X is true, then Y is true as well'. A 'HasA' relation holds when 'X can have or contain Y'. A 'HasProperty' relation holds when 'Y is to specify X'.\n\nEx Input:\nX: call, Y: card_game\n\nEx Output:\nPartOf\n\n\nEx Input:\nX: accident, Y: event\n\nEx Output:\nSynonym\n\n\nEx Input:\nX: beer, Y: liquid\n\nEx Output:\n" }, { "from": "gpt", "value": "HasProperty\n\n\n" } ]

Subsets and Splits

No community queries yet

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