Split (1)

train · 8.3M rows

Search is not available for this dataset

conversations listlengths 2 2
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\n\nSentence 1: The bald-headed lead singer of the band sings into the microphone while the guitarist plays beside him. Sentence 2: An orchestra plays at the theater.\nOutput:" }, { "from": "gpt", "value": "A band is performing and the singer is bald." } ]
[ { "from": "human", "value": "Given a sentence in English language, translate the sentence to Tagalog language keeping the meaning of the original sentence intact.\n\nLet me give you an example: English sentence: Roger Federer was the first player to win 20 Grand Slams\nThe answer to this example can be: Si Roger Federer ang unang manlalaro na nanalo ng 20 Grand Slams\nHere is why: The output is an exact translation of the English sentence to it's Tagalog equivalent and meaning remains the same.\n\nOK. solve this:\nEnglish 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.\nAnswer:" }, { "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": "Compose a new way to ask the same question. The new question must be asking the exact same thing as the original question does. Without any other information, you should be able to tell that the original question and the new question are the same. Preserve bracketed phrases in your new question. You can change the rest of the question provided the above requirements are satisfied. The new question must have a natural, fluent formulation, as if it were composed by a native English speaker. You will be given three pieces of information to help you create better questions. Those are: \"Answer\": the answer to the question, e.g., \"Honolulu\". \"Answer Type\": the type of the answer, e.g., \"Location\". \"Auxiliary Information\" is a detailed description of some concepts mentioned in the question, if any.\n\noriginal question: What car model is [Chevrolet] which and it's related model the [Ford Mustang]?\nanswer: chevrolet camaro\nanswer type: Automobile Model.\nauxiliary information: Chevrolet is a make of automobile produced by General Motors Company.Ford Mustang:;Type: Automobile Model. ;\nWhen it comes to the model of the [Chevrolet] as well as the model of the [Ford Mustang] what are the names of each?\n\noriginal question: what Video Game Engine Developer developed a Video Game Engine that is Used for computer games [Garry's Mod]?\nanswer: valve corporation\nanswer type: Video Game Engine Developer.\nauxiliary information: Garry's Mod, is a sandbox physics game developed predominantly by Garry Newman and later Facepunch Studios. Garry's Mod was originally a modification for Valve's Half-Life 2, but was later made into a standalone game. It is available for Microsoft Windows, OS X and Linux.\nThe computer games [Garry's Mod] uses a video game engine developed by what Video Game Engine Developer\n\noriginal question: What type of holiday is [Christmas and holiday season]?\nanswer: us federal holiday, public holiday in nepal, western christian holiday...\nanswer type: Holiday Category.\nauxiliary information: The Christmas season, also called the holiday season, the festive season, or simply the holidays, is an annually recurring period recognized in many Western and Western-influenced countries that is generally considered to run from late November to early January, defined as incorporating at least Christmas and usually New Year, and sometimes various other holidays and festivals. It incorporates a period of shopping which comprises a peak season for the retail sector, and a period of sales at the end of the season. Christmas window displays and Christmas tree lighting ceremonies when trees decorated with ornaments and light bulbs are illuminated, are traditions in many areas. Originally, the term \"Christmas season\" was considered synonymous with Christmastide, a term associated with Yuletide, which runs from December 25 to January 6, popularly known as the 12 Days of Christmas.\n" }, { "from": "gpt", "value": "What is [Christmas and holiday season] celebrating?\n\n" } ]
[ { "from": "human", "value": "In this task, you're given four sentences of a story written in natural language, and one last sentence (Sentence5). Your job is to classify whether the last sentence completes the rest of the story coherently or not by providing 'Yes' or 'No'.\n\nExample input: Sentence1: Rick grew up in a troubled household. Sentence2: He never found good support in family, and turned to gangs. Sentence3: It wasn't long before Rick got shot in a robbery. Sentence4: The incident caused him to turn a new leaf. \n Sentence5: He is happy now.\nExample output: Yes\nExample explanation: As mentioned in fourth sentence, the incident turned a new leaf to Rick's life; so, he must be happy now.\nQ: Sentence1: Lenny wanted to watch a movie. Sentence2: He drove to the local Hollywood video. Sentence3: Lenny rented three horror movies. Sentence4: Lenny went next door and bought a pizza from a shop. \n Sentence5: When he got home, he prepared to return his three movies.\nA:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "Given a sentence in Dutch, generate a new Dutch sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\n\nOp je trouwdag zou je zeggen dat je van je vrouw houdt." }, { "from": "gpt", "value": "Op je mobiel zou je zeggen dat je je vrouw belt." } ]
[ { "from": "human", "value": "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.\nOne example is below.\nQ: [-83, 53, -48, 8]\nA: [-80, 50, -50, 10]\nRationale: The output correctly rounds each integer in the input list to the nearest ten. So this is a good example.\nQ: [-640, -128, 40, 842, -412, 713, 676, -541]\nA:" }, { "from": "gpt", "value": "[-640, -130, 40, 840, -410, 710, 680, -540]" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given a multiple-choice question and you have to pick the correct option. Answer with option indexes (i.e., \"A\", \"B\", \"C\", and \"D\").\nExample: Deserts are in extremely dry environments, so liquids will naturally be (A) rainbow (B) plentiful (C) meager (D) talented\nOutput: C\nThis is a good example and the output correctly answers the question.\n\nNew input case for you: Playing music at a certain frequency may (A) shatter a glass (B) send sound outside (C) hurt your teeth (D) crack a mirror\nOutput:" }, { "from": "gpt", "value": "A" } ]
[ { "from": "human", "value": "In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time.\n\nInput: Consider Input: Statement: But the largest single federal day-care subsidy is the Dependent Care Tax Credit, which now distributes more than $2. Choices: 1. The subsidy provides tax breaks to parents. 2. The dependent care tax credit is a small federal program. 3. The dependent care tax credit is the largest single subsidy.\n\nOutput: 1\n\n\nInput: Consider Input: Statement: The third-most-visited Gore site, according to Direct Hit, is an Al Gore joke repository, posted on the home page of a GeoCities member and sponsored by the Ripon College Republicans. Choices: 1. The grop agrees with it a.. 2. The College Republicans disagree with everything on the side. 3. The Ripon College Republicans host the GeoCities site.\n\nOutput: 2\n\n\nInput: Consider Input: Statement: Participants also believed that a challenge facing the new PCAOB will be dealing with the complex relationship between federal and state governments involved in regulating the accounting profession. Choices: 1. Participants also believed that the new PCAOB needs to deal with the challenge of regulating interest rates in banks. 2. There is a complex relationship between federal and state governments pertaining to regulating the accounting profession, and participants believed that this is a challenge presented to the new PCAOB. 3. Participants did not believe that the relationship between federal and state governments involved in regulating the accounting profession was a challenge for the new PCAOB.\n\n" }, { "from": "gpt", "value": "Output: 1\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given an article and an answer. Your task is to generate the fill-in-the-blank question for this answer based on the given article. The blanks are always at the end of the question, and can be filled with more than one word or phrase.\nProblem:Article: I shall never forget the night, a few years ago, when Marion J. Douglas was a student in one of my calsses. (I have not used his real name for personal reasons. As he requested.) But here is his real story as he told it before one of our adult - education classes. He told us how tragedy had struck at his home, not once, but twice. The first time he had lost his five-old daughter, a child he adored. He and his wife thought they couldn't bear that first loss; but, as he said:\"Ten months later, God gave us another little girl and she died in five days.\" This double was almost too much to bear. \"I couldn't take it,\" this father told us. \"I couldn't sleep, I couldn't eat, I couldn't rest or relax. My nerves were entirely shaken and my confidence gone.\" At last he went to doctors; one recommended sleeping pills and another recommended a trip. He tried both, but neither helped. He said:\"My body felt as if it was surrounded in a vice , and the jaws of the vice were being drawn tighter and tighter.\" The tension of grief ----if you have ever been paralyzed by sorrow, you know what he meant. But thank God, I had one child left ----a four --year-- old son. He gave me the solution to my problem. One afternoon as I sat around feeling sorry for myself, he asked; 'Daddy, will you build a boat for me?' I was in no mood to build a boat; in fact, I was in no mood to do anything. But my son is a persistent little fellow! I had to give in. Building that toy boat took me about three hours. By the time it was finished, I realized that those three hours spent building that boat were first hours of mental relaxation and peace that I had had in months! I realized that it is difficult to worry while you are busy doing something that requires planning and thinking. In my case, building the boat had knocked worry out of the ring. So I determined to keep busy. The following night, I went from room to room in the house, making a list of jobs that ought to be done. Scores of items needed to be repaired: bookcase, stair steps, storm windows, window-shades, locks, leaky taps. Amazing as it seems, in the course of two weeks I had made a list of 242 items that needed attention. \"During the last two years I have completed most of them. I am busy now that I have no time for worry.\" No time for worry! That is exactly what Winston Churchill said when he was working eighteen hours a day at the height of the war. When he was asked if he worried about his huge responsibilities, he said :\"I am too busy. I have no time for worry.\" \n Answer: he felt tired of adult-education classes\nSolution:" }, { "from": "gpt", "value": "Marion felt his body as if it was caught in a vice because _ ." } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a short article. Your job is to classify the article based on its category. Use the following classification labels, 0. World, 1. Sports, 2. Business, 3. Science or Technical. Label the text \"0\" if it contains information related to world. Label the text \"1\" if it contains information related to sports. Label the text \"2\" if it contains information related business. Label the text \"3\" if it contains science or technical related information. \nQ: Faulds folds as Al Maktoum triumphs The family name alone, Al Maktoum, offered more than a scintilla of suspicion that we could expect something special. Never mind that victory normally materialises in the form of blue-blooded bloodstock rather from the barrel of ...\nA:" }, { "from": "gpt", "value": "1" } ]
[ { "from": "human", "value": "Instructions: In this task, you are given a list of numbers. The list of numbers is separated with comma and inside brackets. You need to remove the maximum(the number with the largest value) and minimum(the number with the smallest value) element from the list and return the list in the same order as input. Your answer should be a list of numbers separated by comma, inside brackets.\nInput: [324, 432, 172, 445, 78, 405, 194, 10, 220, 436, 461, 448, 42, 166, 496, 450, 478, 474, 175, 27]\nOutput:" }, { "from": "gpt", "value": "[324, 432, 172, 445, 78, 405, 194, 220, 436, 461, 448, 42, 166, 450, 478, 474, 175, 27]" } ]
[ { "from": "human", "value": "Definition: 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.\nInput: Valid if , Here is the Zeta - function Hurwitz - Zeta - function and beta is a positive real number .\nValid when , Here the zeta function is Hurwitz zeta function and Beta is a positive real number .\nOutput:" }, { "from": "gpt", "value": "Paraphrase" } ]
[ { "from": "human", "value": "instruction:\nIn 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.\nquestion:\n[254, -866, 839, 743, 235, -603, -886, 519]\nanswer:\n[250, -870, 840, 740, 240, -600, -890, 520]\n\n\nquestion:\n[-110, -797, -493, -425, 687, 614, 556, 352, 18]\nanswer:\n[-110, -800, -490, -420, 690, 610, 560, 350, 20]\n\n\nquestion:\n[-365, -464, -968, -737, -813, 850, 543, 514, 726, 155, 39, -690, 210]\nanswer:\n" }, { "from": "gpt", "value": "[-360, -460, -970, -740, -810, 850, 540, 510, 730, 160, 40, -690, 210]\n\n\n" } ]
[ { "from": "human", "value": "instruction:\nIn this task, you will be given two sentences separated by \"because\". You should decide whether the first sentence can be the result of the second sentence. If you can see a possible cause and effect relationship, answer with \"plausible\", otherwise answer with \"not plausible\".\nquestion:\nthe man held his breath because he was exhausted\nanswer:\nnot plausible\n\n\nquestion:\nthe inside of the train went dark because the sun was shining brightly\nanswer:\nnot plausible\n\n\nquestion:\nthe child caught a life-threatening illness because they didn't know what was going on\nanswer:\n" }, { "from": "gpt", "value": "not plausible\n\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nYou will be given a sentence containing a pronoun/person name and an emotion. From these implicit parameters, the main goal is to find the gender of the person (male / female).\n\nAlonzo feels angry.\nSolution: male\nWhy? The gender of the person is correct and detected mainly based on the name Alonzo.\n\nNew input: Jack told us all about the recent serious events.\nSolution:" }, { "from": "gpt", "value": "male" } ]
[ { "from": "human", "value": "In this task, you are given two statements. The task is to output whether a given textual premise, i.e. Statement 2, entails or implies a given scientific fact, i.e. Statement 1. The output should be 'entails' if Statement 2 supports Statement 1 and should be 'neutral' otherwise.\nExample: Sentence 1: The sum of all chemical reactions that take place within an organism is known as metabolism. Sentence 2: Metabolism is the sum total of all chemical reactions performed by an organism.\nExample solution: entails\nExample explanation: Sentence 2 gives out supporting information about the Metabolism hence it is correct\n\nProblem: Sentence 1: Micronutrients is the term for nutrients the body needs in relatively small amounts, including vitamins and minerals. Sentence 2: They are considered micronutrients because the body needs them in relatively small amounts compared with nutrients such as carbohydrates, proteins, fats and water.\n" }, { "from": "gpt", "value": "Solution: entails" } ]
[ { "from": "human", "value": "In this task, you're given reviews from Amazon's products. Your task is to generate the Summary of the review.\n\nLet me give you an example: My cat won't touch these. My dog, however, chews them and makes a mess all over the carpet and I can't get the shredded sticks out! Messy. Waste of money!\nThe answer to this example can be: Cat hates them\nHere is why: It's a correct summary because the owner's cat hated the product.\n\nOK. solve this:\nWell I really enjoyed this watch until last weekend in Moab. While sitting in the relaxing hot tub my watch screen went blank and the watch started to vibrate. I have tried multiple remedies. I believe it is no longer good.\nAnswer:" }, { "from": "gpt", "value": "Well I really enjoyed this watch until last weekend in Moab" } ]
[ { "from": "human", "value": "Detailed Instructions: 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'.\nSee one example below:\nProblem: Query: Tell me about defender \n Clarification: are you referring to the arcade game called defender\nSolution: Yes\nExplanation: The given clarification properly clarify the query. Hence, the output is Yes.\n\nProblem: Query: Tell me information about Volvo. \n Clarification: would you like a list of websites that show workouts for elliptical trainers\nSolution:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you're given a review from Amazon's food products. Your task is to generate a rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral or mixed, 4: good, 5: extremely good. \n\nMy child was exclusively breastfed for 4 1/2 months and I gradually introduced Similac Organic formula to supplement (my breastmilk started to dry up). She found this was so much easier to eat she gave up on me by 5 1/2 months. By the time I completely stopped nursing she was so constipated from the formula that I switched. She winced and cried and worked so long to just produced a hard ball the size of ping pong ball. It was horrible! I realized I was the one helping her poo with nursing and then she lost all ability when she went full-formula. I say switch....\nOutput:" }, { "from": "gpt", "value": "1" } ]
[ { "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: \"The Palestinian Authority is not functioning in the Gaza Strip, there is no guiding hand,\" Mofaz was quoted as saying by the Yediot Aharonot daily. \"The Palestinian security forces are not obeying the instructions of the PA chairman (Abbas). Question: What happened after Mofaz was quoted? Events: ['functioning', 'is', 'quoted', 'saying', 'obeying']\n" }, { "from": "gpt", "value": "Solution: " } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, a passage will be given and the goal is to identify an event from the passage. An event is defined as a single word representing something that happened, is happening, or may happen. An event can be factual or hypothetical, positive or negative, certain or uncertain. While most events are based on verbs, an event can also be based on a noun (ex. storm, snow, rainfall) or a copula verb (is, was, been, etc.). The event must not be a pronoun or an adjective. For noun events with multiple words, use the last word in the phrase as event.\n\nPassage: Poland, Hungary and the Czech Republic are scheduled to become full members of NATO in April next year when the alliance celebrates its 50th anniversary in Washington. \nOutput:" }, { "from": "gpt", "value": "scheduled" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task you will be given a list of integers. You should remove any integer that is not prime. A prime integer is an integer that is only divisible by '1' and itself. The output should be the list of prime numbers in the input list. If there are no primes in the input list an empty list (\"[]\") should be returned.\n\n[666, 54, 138, 864, 937, 702, 699, 79, 811, 419, 17, 619, 163, 103, 643, 691]\nOutput:" }, { "from": "gpt", "value": "[937, 79, 811, 419, 17, 619, 163, 103, 643, 691]" } ]
[ { "from": "human", "value": "Detailed Instructions: 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.\nProblem:password = 3TmCnQCcYAKtG39oG5NCzxCFCMqAWxcJ\nSolution:" }, { "from": "gpt", "value": "12" } ]
[ { "from": "human", "value": "Definition: 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].\nInput: Post: @MSNBC Protect USA from illigal refugees - thank you Mr.Trump !\nOutput:" }, { "from": "gpt", "value": "Generic" } ]
[ { "from": "human", "value": "In this task you will be given a list of numbers and you need to subtract every value in the list with the index it is at. The index of an elements shows its numerical order in the list(for example, in the list [7,10,4,5], the index of 7 is 1 and the index of 4 is 3) You should start the index at 1, so the first element in the list will be subtracted by one. For every element in the list you need to find \"element - index\" where the index of the beginning element is 1 and increments by 1 for each element. Put your result list in brackets.\n\nExample Input: [-3, 3, -4, 19, 15, 12, -10, -17]\nExample Output: [-4, 1, -7, 15, 10, 6, -17, -25]\n\nExample Input: [0, 6, -5, 5, -16]\nExample Output: [-1, 4, -8, 1, -21]\n\nExample Input: [-10, 16, 19, -4, -12, 20, -15]\nExample Output:" }, { "from": "gpt", "value": "[-11, 14, 16, -8, -17, 14, -22]\n\n" } ]
[ { "from": "human", "value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair neither agree nor contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\n\nSentence 1: Someone is looking out their window watching the mailman deliver their mail and drive on to the next house. Sentence 2: The postal worker is driving a truck." }, { "from": "gpt", "value": "The mailman is wearing a blue hat." } ]
[ { "from": "human", "value": "instruction:\nIn this task, you will be presented with a question, and you have to write the part-of-speech tag for each word in the question. 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\nquestion:\nHow many songs were in the 1996 work ?\nanswer:\nWRB JJ NNS VBD IN DT CD NN .\n\n\nquestion:\nWhat is the year of birth of the player with the most National Football League career rushing yards ?\nanswer:\nWP VBZ DT NN IN NN IN DT NN IN DT RBS NNP NNP NNP NN VBG NNS .\n\n\nquestion:\nWhat is the national rank in terms of number of flyers of the airport that received 751,791 flyers from the airport in Gimhae in 2018 ?\nanswer:\n" }, { "from": "gpt", "value": "WP VBZ DT JJ NN IN NNS IN NN IN NNS IN DT NN WDT VBD CD NNS IN DT NN IN NNP IN CD .\n\n\n" } ]
[ { "from": "human", "value": "In 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.\nExample: [2,5,1,4],[2,5,8,4,2,0]\nExample solution: [2,4,5]\nExample explanation: The elements 2,4, and 5 are in both lists. This is a good example.\n\nProblem: [3, 9, 10, 3, 8] , [8, 8, 3, 3, 6]\n" }, { "from": "gpt", "value": "Solution: [3, 8]" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you need to provide the correct option for a given problem from the provided options.\nSee one example below:\nProblem: Problem: jo ' s collection contains us , indian and british stamps . if the ratio of us to indian stamps is 6 to 2 and the ratio of indian to british stamps is 5 to 1 , what is the ratio of us to british stamps ? \nOptions: a ) 5 : 1 , b ) 30 : 2 , c ) 15 : 2 , d ) 20 : 2 , e ) 25 : 2\nSolution: b\nExplanation: \"u / i = 6 / 2 i / b = 5 / 1 since i is multiple of both 2 ( as per first ratio ) and 5 ( as per second ratio ) so let ' s assume that i = 10 i . e . multiplying teh first ratio by 5 and second ration by 2 in each numerator and denominator then , u : i : b = 30 : 18 : 2 i . e . u : b = 30 : 2 answer : option b\"\n\nProblem: Problem: if $ 1088 are divided between worker a and worker b in the ratio 5 : 11 , what is the share that worker b will get ? \nOptions: a ) 62.45 % , b ) 64.55 % , c ) 66.65 % , d ) 68.75 % , e ) 70.85 %\nSolution:" }, { "from": "gpt", "value": "d" } ]
[ { "from": "human", "value": "Definition: You will be given a trivia clue, and the category it belongs to. You should answer with the best answer that belongs in the category and is described by the clue. For simplicity, answers should be in all lower cased letters.\nInput: Category: LYRICS OF THE ARTIST \nClue: \"Are you going to let it all hang out? Fat bottomed girls, you make the rockin' world go round\"\nOutput:" }, { "from": "gpt", "value": "queen" } ]
[ { "from": "human", "value": "Instructions: You are given an amazon food product review and its polarity (positive or negative). Your task is to answer \"True\" if the specified sentence and its polarity match; otherwise, answer \"False\".\nInput: They have some textured powder stuff on them that makes them taste bad.. bad after taste. I guess it's so they don't stick together. Never again \n Polarity: Negative\nOutput:" }, { "from": "gpt", "value": "True" } ]
[ { "from": "human", "value": "Given a sentence, generate what should be the most likely next statement. The next statement should be reasonable and logically correct.\nOne example: We notice a man in a kayak and a yellow helmet coming in from the left. As he approaches, his kayak \nSolution is here: flips upside - down\nExplanation: Flipping of the kayak is a probable event. It is a logical next statement, given the context.\n\nNow, solve this: The protective shield, the burning wooden ground stones at the Quidditch Pitch illuminate the dark hillside. Illusions\nSolution:" }, { "from": "gpt", "value": "continue to pound against the shield." } ]
[ { "from": "human", "value": "Instructions: Given a sentence in English language, translate the sentence to Somali language keeping the meaning of the original sentence intact\nInput: English sentence: 30 And it came to pass, while they were in the way, that tidings came to David, saying, Absalom hath slain all the king's sons, and there is not one of them left.\nOutput:" }, { "from": "gpt", "value": "30 Oo intay sii socdeen ayaa war u yimid Daa'uud, oo waxaa lagu yidhi, Absaaloom wuxuu laayay wiilashii boqorka oo dhan, oo mid qudhuhuna kama hadhin." } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task you will be given a list of integers. You should only return an integer if the first digit is the same as the last digit in the number. If an integer has a single digit, then it should be returned. If there are no integers that start and end with the same digit then an empty list (\"[]\") should be returned.\n\n[-638, 103, -290, 946, -572, 123, -913, 739, 283, -607, 961, 830, 256, -873, 975, 706, 643, -276, 923, 17, -849, 144, -581]\nOutput:" }, { "from": "gpt", "value": "[]" } ]
[ { "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: threat and non-threat. Threat is a statement that someone will be hurt or harmed, especially if the person does not do something in particular.\n\nExample input: Comment: Enough already. Cut the head off this snake.\nExample output: Threat\nExample explanation: This comment conveys a violent threat to someone.\nQ: Comment: Bristol would just punch her abuser in the jugular.\nA:" }, { "from": "gpt", "value": "Threat" } ]
[ { "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\nLet me give you an example: 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\nThe answer to this example can be: true\nHere is why: 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.\n\nOK. solve this:\nnews:The robust growth was the result of the inclusion of clothing chain Lindex in the Group in December 2007 .\npolarity:positive\nAnswer:" }, { "from": "gpt", "value": "true" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: threat and non-threat. Threat is a statement that someone will be hurt or harmed, especially if the person does not do something in particular.\nQ: Comment: Depressed middle aged men often isolate themselves, express anger, agitation, bitterness and drink too much. Instead of being properly identified as depressed (a label many of them would reject) they are derided as being jerks. Unlike some other demographics they may not advertise their wish to die, just act on it. Depression in men is not understood, nor is it recognized as the serious health problem it is.\nA:" }, { "from": "gpt", "value": "Non-threat" } ]
[ { "from": "human", "value": "You will be given a sentence. Check whether the sentence is grammatically correct and is meaningful. If the sentence is grammatically correct, then answer with '1', otherwise answer with '0'.\n\nLet me give you an example: Our friends won't buy this analysis, let alone the next one we propose.\nThe answer to this example can be: 1\nHere is why: Since all the entities are in thier correct positions the statement is grammatically correct.Hence, the output is 1.\n\nOK. solve this:\nFluffy is sick, which it is certain that no one here realizes.\nAnswer:" }, { "from": "gpt", "value": "1" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Given a text paragraph and a fact, generate 'True' if the fact can be inferred/concluded from the paragraph, otherwise generate 'False'. The input passage contains as set of logical statements so the fact can be marked either 'True' or 'False' if the relavant info regarding the fact is present in the given passage. If the Fact can't be marked True or False from the given paragraph, mark it as False. Don't use knowledge outside the given paragraph to check the fact.\n\nParagraph: If someone is not green and not cold then they are white. Charlie is cold. Charlie is not quiet. Charlie is round. Charlie is red. Charlie is green. If someone is nice then they are green. White, nice people are green. If someone is quiet and not cold then they are green. Charlie is nice. If someone is not round then they are not nice. All white, green people are not quiet. Charlie is white. If someone is not nice then they are quiet. If Charlie is round then Charlie is white. Question: Charlie is quiet.\n" }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "Teacher:Given 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.\nTeacher: Now, understand the problem? Solve this instance: walk twice after look opposite left twice\nStudent:" }, { "from": "gpt", "value": "I_TURN_LEFT I_TURN_LEFT I_LOOK I_TURN_LEFT I_TURN_LEFT I_LOOK I_WALK I_WALK" } ]
[ { "from": "human", "value": "Detailed Instructions: You are shown a conversation between a user and system. Identify who has spoken the indicated sentence based on the conversation.\nProblem:Sentence1: Good bye Sentence2: thank you. good bye. Sentence3: The dojo noodle bar serves asian oriental food. They are located at 40210 Millers Yard City Centre and their phone number is 01223 363471. Sentence4: i want somewhere that serves traditional food. Sentence5: There are no traditional restaurants in the city. Can I help you with a different type of cuisine? Sentence6: How abou asian oriental food Sentence7: There are 5 restaurants meeting your criteria. What area and price range did you have in mind? Sentence8: What is the address and phone number? Question: Who has spoken the sentence 3? (A) User (B) System\nSolution:" }, { "from": "gpt", "value": "Answer: (B) System" } ]
[ { "from": "human", "value": "Teacher:In this task, you're given a review from Amazon. Your task is to generate a rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral, 4: good, 5: extremely good.\nTeacher: Now, understand the problem? Solve this instance: When I pull the yarn through, it gets stuck on the light. The light should be moved back on the hook about a half inch. Nice concept; just didn't work for me.\nStudent:" }, { "from": "gpt", "value": "3" } ]
[ { "from": "human", "value": "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.\nOne example: [-83, 53, -48, 8]\nSolution is here: [-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\nNow, solve this: [919, 956, -219, 515, 441]\nSolution:" }, { "from": "gpt", "value": "[920, 960, -220, 520, 440]" } ]
[ { "from": "human", "value": "Detailed Instructions: You are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to choose the correct answer to the question based on the passage. Answer of the question cannot be found directly from the passage, it is indirectly indicated in the passage. Do not answer with words other than the two options, and do not answer with option titles(e.g. \"option1\" or \"1\" are not acceptable answers.)\nQ: Passage: A friend was moving from her house to an apartment in the city . She called several friends to help move , making sure that at least one of them had a truck or van that could hold large pieces of furniture , We all met at her house on Saturday . There were five of us , including her , with one pick-up truck , and one small minivan . There were several large items , a bed and dresser from the bedroom , and a sofa and loveseat from the living room . There were also smaller things , such as dining chairs , and a television . We decided to start with the larger items first , because they would be more difficult and to fit in the vehicles . It was a lot of work , and took all day , but we finally got everything stuffed into the van and truck . We were so tired , we decided to wait until the next day to drive to the new apartment and unpack everything ! Question: When could they put the smaller items in, alongside the bigger ones? Option1: Before the bigger ones Option2: after the big items were loaded\nA:" }, { "from": "gpt", "value": "after the big items were loaded" } ]
[ { "from": "human", "value": "Detailed Instructions: Given a simple high-school level math question, you are required to solve it and provide the final answer. The final answer is always a single number. These questions can range from a variety of topics like simple arithmetic, solving equations, converting a quantity from one unit to another, finding remainders/GCD/LCM, finding probabilities etc. Each question has only one correct answer. This answer can be a positive or negative integer, a fraction or a decimal number. If the answer is a negative number use the hyphen (e.g. -42) symbol for the minus sign. For decimal numbers, do not add extra zeros after the decimal point. For fractional numbers, separate the numerator and denominator using a forward slash (e.g. 3/25).\nProblem:Solve 0 = -p + 1, -38 + 15 = 5h + 2p for h.\nSolution:" }, { "from": "gpt", "value": "-5" } ]
[ { "from": "human", "value": "Instructions: In this task you are given a list of triplets of the form [subject, predicate, object] and the output should be a question based on the triplets but with the subject and/or object replaced with blanks (represented using two or more consecutive underscores). Triplet values encompassed in [*] are special tokens that can be replaced with synonyms. The objective is to construct a question in a manner that (a) captures the facts specified in at least one of the triplets, and (b) ideally contains a limited number of blanks such that it is a well-formed question that is easy to answer. A blank can represent a single word or a phrase.\nInput: [['The Rice Boat', 'eatType', 'restaurant'], ['The Rice Boat', 'food', 'French'], ['The Rice Boat', 'customer rating', '3 out of 5'], ['The Rice Boat', 'area', 'riverside'], ['The Rice Boat', 'familyFriendly', 'yes']]\nOutput:" }, { "from": "gpt", "value": "_____ is a French restaurant located in the area of Riverside. This restaurant is children Friendly and has a customer rating of 3 out of 5." } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task you will be given an arithmetic operation and you have to find its answer. The symbols of operators '+' and '-' has been swapped i.e you need to perform subtraction when you see a '+' symbol and addition in case of '-' symbol.\n\n5 + 3\nSolution: 2\nWhy? Here, '+' represents subtraction operation. So, the answer is 2 (5-3=2).\n\nNew input: 9191 - 18 + 3055 + 1188 - 9309 - 1293\nSolution:" }, { "from": "gpt", "value": "15568" } ]
[ { "from": "human", "value": "Teacher:Given two entities as input, classify as \"yes\" if second entity is the part of the first entity. Otherwise classify them as \"no\". These are entities of meronym In linguistics, meronymy is a semantic relation between a meronym denoting a part and a holonym denoting a whole. In simpler terms, a meronym (i.e., second entity) is in a part-of relationship with its holonym (i.e., first entity).\nTeacher: Now, understand the problem? Solve this instance: Entity 1: substance \n Entity 2: bee 's wax\nStudent:" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "In this task, you are given a Reddit post as a text. Your task is to generate a title for this text. The title should start with \"TIFU by\", followed by a situation that caused humor. The title should contain 7-12 words, ideally.\n\nQ: Text: so of course this happened a while ago. it had actually been when the xbox 360 had just been released. my parents bought us one for a present right after it came out and about a week after receiving it we were to go on vacation to hawaii for a month. i decided i wanted to take my xbox so i had stuff to do at night and because i was a kid and it just came out. anyways fast forward a bit and my family and i are at the airport where my grandmother (bless her) is having a terrible time getting through the metal detectors (she decided to wear like a million pieces of jewelry for some odd reason). eventually we get all of the metal removed from her and she gets through after about like 6 attempts lol. when we drop our luggage off they sent them through the xrays or w.e detectors as well and at this point security comes and pulls us to the side. after rigorous questioning they soon reveal to us that we are carrying multiple suspicious items and that they are going to search our bags. we spend what seems like forever being searched when they finally pull the xbox out of our bag and are about to begin pulling it apart. at this point i begin to cry because we are being questioned and people are about to tear into my brand new xbox 360. not only are they searching me and my brothers but they are searching my poor grandmother too due to the fact that she had to go through the metal detector a few times and was deemed suspicious. after tons of arguing my dad finally convinces them that his son (and grandmother) is not brining a bomb on board via an xbox 360.\nthey gave us a stern talking to and sent us on our way where i spent my nights getting trippy on prey\n\nA: TIFU by bringing an xbox 360 to an airport\n***\nQ: Text: ok, so this didn't happen today, but it happened and that is the main. \n\nit was the summer of 2011 and i had just finished my first year of university and had come home for the summer. my parents are separated and both have awkward living arrangements (my dad works out of town & my mum didn't have her own place for me to stay) so there was a plan put in place for me to stay with my grandmother for most of the summer. she didn't have any internet installed and so they even went as far as to get a 3 month contract with the suppliers so i would feel somewhat at home in my new, floral surroundings.\n\nso anyhow, i move in my desk, imac, speakers etc and after a few days of playing music & games etc my gran approached me and told me that whatever i was doing was too loud - so being in a position of compromise, i bought some new headphones. i was studying film production at the time and spent a lot of time editing my films, so i was due some new cans anyhow. so i made a point of buying the most anti-social headphones on the market, and landed on some real nice hq noise-cancelling motherfuckers (you can see where this is going immediately). everyone was a winner, my gran was left in peace to do whatever the fuck she was doing and vice-versa.\n\na lot of my nights were spent playing football manager until the early hours, with added bouts of facebook & youtube in-between. this one particular evening i had taken sheffield wednesday to the european cup final and was manic with delight, so much so i even considered suiting up for the actual final - yeah, i know.. so during one of my trawls through facebook i caught a glimpse of a picture of a girl i used to go to school with, she was pretty, very pretty in-fact, but her morals were always very low, somewhere near her ankles, much like her underwear, i imagine. i sat up in my seat and felt the brush of my jogging pants against my pipe, sending one of those lightning feelings of sexual hedonism right through me, as if all of my sexual being had aligned like planets and stars. i knew my destiny, and it was to slap my ham, right there, right then.\n\ni quickly searched out the first porn site on my mind and set about finding a girl who bared as much resemblance to her as humanly possible, which as most men will agree, quickly dwindled into me clicking a thumbnail that featured a girl with the same hair colour. the joy of having a huge screen is that i can pull one of the tabs to the left of the screen and the other to the right, allowing me to indulge in both pornography and a slightly out of focus image of my whore queen at the same time, hoping that during my session the whole thing will ripple dissolve into one huge, grotesque fantasy before me. i was ready.\n\ni put the volume to just two notches shy of the jackpot and hit play, i even allowed for some build up to allow me the time to pull down my pants and position my feet and legs into a place of comfort. fuck, did these headphones deliver! the quality was so high that if you listened really carefully between the pounding of adult flesh, you could just about hear the anguished tears of melanie rios' father hit the ground. i was in heaven. the whole thing lasted for what seemed like eternity, the rhythmic fucking, the swirls of moans through my ears, the coy smile of my queen. the ship was coasting steadily until something really fucking hot happened in the film and that was it, the countdown to launch began. there is no going back from this point. mission control were pumping images into my head that i never even knew i was capable of thinking. i closed my eyes and could feel the launch coming, 5, 4, 3.. i was now doing everything in my physical power to delay take-off, just to make it all the better. and then, bang. euphoria. i was floating through space, mission accomplished. i still for some reason imagine gary sinise as houston, saluting me as a tear fills his eyes. with my eyes tight shut and my toes curled into the carpet, i shot at least 5 ropes onto myself. there wasn't any need for me to care, i had a sock somewhere nearby. once i had mopped myself down, starting with a little dabbing of the brow, i slipped off the cans and took a deep breath. i could still hear the whines of miss rios through the evacuated headphones and so i closed off the page. i was met by the eyes of innocence to my right, the mona lisa to my twisted art, she looked a lot less appealing this time around. i pursed my lips and gave a slight nod of appreciation as i closed her off too. life was good.\n\nor so i thought..\n\ni turned in my chair to leave the room for the bathroom, and that's when i saw it. a cup of tea sat steaming on my bedside table, beside it was a snack sized peanut mighty bar (for those of you that are wondering, a peanut mighty is basically a snickers but less glamorous, you don't find them anywhere, the perfect criteria for any chocolate or sweets you're likely to find at your grandparents place.) this made the whole thing worse. at some point during take-off, with my eyes clasped shut, my gran has walked into my room bearing hot beverages and obscure chocolate peanut snacks and caught me shooting ghost ropes all over my creased stomach via the video of a latino in reverse cowgirl and a blurry image of a girl she's watched grow up with me throughout school. she had been shouting of me from the bottom of the stairs to come and grab the impromptu snacks and when i didn't respond, she got worried and decided to hand deliver them. if this isn't fucked up for any of you by this point, i'd like you all to know that my gran is basically crippled with arthritis and it takes her 3x longer to do things than most able bodied people. so after climbing what must have felt like mount everest to her, she reached the summit and found her grandson pulling himself around the computer chair by his own cock.\n\nyou never recover from things like this, i promise you.\n\nedit: i've just been linked a video from a ricky gervais skit that is basically the same story. i can absolutely assure you that this is 100% true, i have too limited a time on planet earth to make up stories about my gran catching me beat off.\n\nA: TIFU: by jacking off with my headphones on\n*\nQ: Text: obligatory this didn't happen today, but years ago when i was 16. tldr at bottom, this is a long one so brace yourself. typing this on my phone, so please excuse grammatical errors.\n\nnow for some back story:\n\nthe day was like most beautiful, summer days. my friend, we'll call him allan, and i are hanging out. i must note that allan and i were possibly the worst combination in a group of friends be hanging out.\n\nimagine allan. allan is the guy you were envious of during your youth. he was better at shenanigans than you and a complete guru when it came to getting away with the shenanigans. he was sure to have more fun than you.\n\nnow i consider myself in the group of friends to kind of mirror allan, with the exception of more care of intelligence, so it has always been easy to say i was the brains of the operation we him and i were on our daily missions. brilliant ideas to kill the time with were my bread and butter.\n\njack was the new kids on the block, having only moved to our town a month ago. the son of a single mom, living on a wicked tight budget. with that being said, you could assume he was probably far more mature and/or scared so he was not blessed enough to enjoy our teen shenanigans. always grounded because his mother cared far more than a healthy amount about the kids future and success.\n\nthe story:\n\nallan and i would hang out, for days and weeks, without thinking twice about it. at the time i'd even practically lived with him and his super christian family for about a month. staying the night every night, and even having a decent wardrobe at his house.\n\nwe'd wake up at about 3 in the afternoon every day, find our group of friends, and then as teenagers do, we'd kill the time as efficiently as possible. and then our group of friends would hit there curfew, and it'd just be allan and i, hanging out and killing time until about 5am. this was a daily occurrence.\n\nbut then it happened. the new kid on the block decided he'd finally had enough envy, and wanted to give our shenanigans a try. through lobbying, negotiation, and blackmail he convinced his uber strict mother to let him stay at allans house for the night. \n\nnow we lived in small town u.s.a. at the time, so our shenanigans, while hilarious, would often go unnoticed. little did allan and i know, we'd set a running record in this town. allan and i had set a record for highest shoplifting on a spree of stores out of pure boredom. being used to this, our go-to was the one gas station we had in town. it was open 24 hours and being up all night in a small town enabled is to easily become comfortable, and even professional at stealing candy from this gas station.\n\nwe'd been to the gas station 4 or 5 times on this night. buying one thing and stealing 10, obviously the most efficient. though on our last trip, things took a turn for the worst. jack had gotten comfortable with our routines. even excited. we had broken the morals of society on fresh blood and our egos shot through the roof.\n\nnow the fu. we'd all hit a new high, a better adrenaline rush. and we had started walking through town to see if a friend on the other side of town was still awake. while walking, we began to pre plan incase anything went sideways. if trouble incurred, we'd split up, cause confusion, and meet back up at the town mcdonald's, which had closed for the night. fool proof plan right? we'll get to that.\n\nour friend on the other side of town wasn't awake, so we start heading back to the gas station to kill time. while this journey wasn't very long, our adrenaline died down and we'd grown bored. then it happened. allan, with far too many skittles decided to start a good fight. we had our fun and moved on. only allan wasn't yet done.\n\ni remember this like it was yesterday. while walking i look over and allan lights up with joy. a semi truck was coming up behind us, and he'd gotten the idea to see who had the biggest balls of them all. slowmo and all, allan tosses the skittle, just in time for it to smack into the semi truck. surely it wouldn't phase something so big. but it did.\n\nthe semi truck locks all 18 wheels in the middle of town at 4 in the morning. havoc breaks loose and we all split up. i made it to mcdonald's first, and waited. coast clear, no problems, the night continues. then jack. then... no allan. 10 minutes. 20 minutes. even 30. so naturally we'd assumed he just got confused and went home.\n\nso jack and i make the epic adventure of getting to alan's house through shadows, backyards, and side streets. we made it, but still, no allan. so 10 minutes, 20, and even 30 go by with no sign of allan. we begin to panic. he must've got nabbed on his way. so we suit up in gilleys and flashlights and pull a full search party for him.\n\nwe start walking and were thinking for sure he's at the gas station by now. while cutting a corner through an alley in attempt to stay in the shadows we stumbled upon a police car. feet away from the car, and in pitch blackdarkness, we couldn't tell where the officer was. so we come out of hiding and start to turn back and boom. the cop was behind us the whole time. the second we turn around were blinded by what can only be described as heavens beam upon welcoming to heaven. gun drawn the police made us get on the ground and proceeded to arrest us.\n\nafter an hour or two longer, jacks mom picked him up from the police station, furious as ever. the cops knew i was practically living with alan and after failing to contact my parents decided to just contact his. success.\n\nalan's mom was sitting on the porch when the cop dropped me off and explain the situation. she proceeded to ground me, as she would her own children, when they're in trouble. it was funny to say the least. no further incidents the rest of the night.\n\nallan was finally at home when i'd been delivered like your favorite package on christmas. laughing hysterically at me for getting nabbed. allan had gone home first. sat and waited for us and then after about a half hour remembered we had the plan to meet at mcdonald's. except he didn't take the shadows to get there. when he does get there, we were nowhere to be found, so naturally he goes to the gas station. still nothing. on his way back home, he spots us getting arrested and the rest is downhill from there.\n\nafter that night, jack, potentially our trifecta of shenanigans, was perma-shunned from our existence. still living in town, but never to be seen again. allan and i had a cool story to tell our friends and overall it was a good night.\n\nthen the repercussions. while trying to enlist in the military, my security clearance kept having issues. it took forever (almost 2 years) to enlist when it should've only taken 2 months. my fu from years earlier did come back to bite me, but only temporarily. now i've got kids of my own, and i hope i'm a cool enough dad to hear their epic adventure stories when they start causing a ruckus.\n\nA:" }, { "from": "gpt", "value": "TIFU by stealing the rainbow in excess\n**\n" } ]
[ { "from": "human", "value": "Q: Given a sentence, fill out the missing word with a 'no' or a number (between zero and ten). You should write the numbers with english alphabet, like: four instead of 4.\nWomen can have hot flashes or insomnia ____ years before they have their last menstrual period.\nA:" }, { "from": "gpt", "value": "ten" } ]
[ { "from": "human", "value": "TASK DEFINITION: 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\nPROBLEM: Context Word: signs.\n\nSOLUTION: Sentence 1: The signs all pointed towards a rainy day, not a sunny one, and it did end up _ . \nAnswer1: rainy. \nSentence 2: The signs all pointed towards a rainy day, not a sunny one, although it did end up _ . \nAnswer2: sunny.\n\nPROBLEM: Context Word: Guinea pig.\n\nSOLUTION: Sentence 1: The hamster was active but the guinea pig died because the _ was too old. \nAnswer1: guinea pig. \nSentence 2: The hamster was active but the guinea pig died because the _ was still young. \nAnswer2: hamster.\n\nPROBLEM: Context Word: golfer.\n\nSOLUTION:" }, { "from": "gpt", "value": "Sentence 1: The golfer decided to buy new shoes, but not clubs, because his _ were worn. \nAnswer1: shoes. \nSentence 2: The golfer decided to buy new shoes, but not clubs, because his _ were newer. \nAnswer2: clubs.\n\n" } ]
[ { "from": "human", "value": "Part 1. Definition\nTurn the given fact into a question by a simple rearrangement of words. This typically involves replacing some part of the given fact with a WH word. For example, replacing the subject of the provided fact with the word \"what\" can form a valid question. Don't be creative! You just need to rearrange the words to turn the fact into a question - easy! Don't just randomly remove a word from the given fact to form a question. Remember that your question must evaluate scientific understanding. Pick a word or a phrase in the given fact to be the correct answer, then make the rest of the question. You can also form a question without any WH words. For example, \"A radio converts electricity into?\"\nPart 2. Example\nFact: pesticides can harm animals.\nAnswer: What can harm animals?\nExplanation: It's a good question because it is formed by simply replacing the word \"pesticides\" with \"what\".\nPart 3. Exercise\nFact: parasites remove waste from their bodies.\nAnswer:" }, { "from": "gpt", "value": "What do parasites do with waste?" } ]
[ { "from": "human", "value": "You will be given a trivia clue, and the category it belongs to. You should answer with the best answer that belongs in the category and is described by the clue. For consistency, answers should be in all lower cased letters.\n\nInput: Consider Input: Category: GOLF \nClue: In golfing slang, to use a \"Texas wedge\" is to use this club when not on the green\n\nOutput: a putter\n\n\nInput: Consider Input: Category: MOVIE MR. & MRS. \nClue: It's the title couple played by Brad Pitt & Angelina Jolie in a 2005 movie\n\nOutput: mr. & mrs. smith\n\n\nInput: Consider Input: Category: PLANES, TRAINS & AUTOMOBILES \nClue: This Carroll Shelby design \"snaked\" along as the only American car to win the FIA Grand Touring Championship\n\n" }, { "from": "gpt", "value": "Output: the cobra\n\n\n" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you are given an item and you need to check whether it is edible or not, return 1 if it is edible, else return 2.\n\nteddy bear\n" }, { "from": "gpt", "value": "2" } ]
[ { "from": "human", "value": "Definition: In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. There are several possible answers, you'll need to choose the proper one. Carefully read the given text, pay special attention to the marked number, think about what (unwritten) information the marked number holds inside, choose the most adequate word(s) from the optional answers. If none of them seems right to you, there's also an option for other. If your answer is \"REFERENCE\", also write the reference entity, otherwise write the implicit option name. Options to choose from are:\nREFERENCE: Some object which is being mentioned in the text before or after the target number. The reference answer has a higher priority than any other. If both Reference and another answer are possible, prioritize the Reference.\nYEAR: Describing a calendric year\nAGE: Describing someone's age\nCURRENCY: Reference to some monetary value e.g dollar, euro etc.\nPEOPLE: Describing a single/plural persons\nTIME: Describing a time of the day. Usually you can add the word o'clock after those numbers.\nOTHER: Some other option, which isn't listed here.\nInput: Otto Flagler: I use what is called \" Hadake - Jine \" - the Naked Choke . It has to be done very carefully ... just right . One arm goes around the throat - so . And with the other I grab my other arm - so , and with my hand I press on the neck - so . The breathe is cut off ; he is paralyzed . Paralyzed , he can not make a sound . That 's when you take the wallet . It has to be done very carefully . the pressure has to be applied just so much , just so long . Under no circumstance must one snap the neck - that can happen very easily is one gets excited . If _ one _ is not careful , the man is not unconscious , but dead .\nOutput:" }, { "from": "gpt", "value": "PEOPLE" } ]
[ { "from": "human", "value": "Q: 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 Person1: Amanda , how do you like this peaked cap ? \n Person2: Didn't you say you want to buy a top hat ? \n Person1: But I think this one fits me Well . Why don't you try on the sombrero in black ? \n Person2: I don't like caps at all . \nA:" }, { "from": "gpt", "value": "1" } ]
[ { "from": "human", "value": "In this task, you are given a question and answer for that. The answer will fill in the blank or will complete the unfinished question. Your task is to provide an explanation based on the given question or fill-in-the-blank statement, and answer.\n\nExample input: 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 Answer: rise\nExample output: The carbon taxes encourage people to use less fossil fuel, which reduces carbon dioxide emissions.\nExample explanation: As mentioned in the input Question and Answer, the output statement constructs the explanation correctly. By decreasing the taxes, carbon dioxide emissions will rise, so the explanation is correct. \nQ: Question: Chris sees a particle with great energy. Chris knows it has lots of energy because it vibrates \n Answer: powerfully\nA:" }, { "from": "gpt", "value": "The more energy the particles in matter have, the faster and more strongly they vibrate." } ]
[ { "from": "human", "value": "In this task, you will be presented with a passage and have to answer a question based on your understanding of the events inferred from the passage. Among the entities, try to find the best entity that is most likely to fill in \"_\" and classify the answers based on options.\n\n(CNN) Khuram Shahzad Butt, a 27-year-old British national born in Pakistan who died in a hail of police bullets Saturday night after the London attack, was a tall, lanky, straggly bearded young man of few words -- a brainwashed follower of al-Muhajiroun, a loose grouping of British extremists supportive of ISIS linked to a large number of terrorist plots involving UK nationals. The latest on London attack CNN's Sandi Sidhu met him several times while reporting on the group in the United Kingdom between 2014 and 2016. He went by the name \"Abz\" or \"Abu Zaitun\" and seldom spoke during meetings. He was content to leave the task of proselytizing to louder, older members of the group, according to Sidhu.London attacker Khuram Shahzad Butt appeared in a 2016 Channel 4 documentary called \"The Jihadis Next Door\"At the time of the attack, Butt worked as a receptionist at a fitness center in Ilford, a friend from the gym said \n Questions:The identification of Butt as one of the attackers raised many questions about what _ authorities knew about him and when. (A) CNN (B) Khuram Shahzad Butt (C) British (D) Pakistan (E) London (F) Muhajiroun (G) ISIS (H) UK (I) Sandi Sidhu (J) United Kingdom (K) Abz (L) Abu Zaitun (M) Sidhu (N) Channel 4 (O) The Jihadis Next Door (P) Butt (Q) Ilford" }, { "from": "gpt", "value": "(C)" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task you will be given a text passage from a trivia quiz. You should choose the category this question belongs to from these categories: History, Science, Social Science, Fine Arts, Literature. You can only choose one category, so if in doubt, please choose the closest match.\n\nA malfunction in CFTR's uptake of sugar groups at this site is a primary mutation associated with cystic fibrosis. It recognizes and designates destination based on the presence of a hydrophobic signal sequence or signal recognition particle. Enclosing a sac known as the lumen, this structure was once known as the gastroplasm. It consists of two phospholipid bilayers and the presence of ribosomes differentiates its two types. FTP, name this transport network within the cytoplasm, divided into smooth and rough varieties.\n" }, { "from": "gpt", "value": "Science" } ]
[ { "from": "human", "value": "Instructions: You 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\".\nInput: Which country is the largest country in Latin America ?\nOutput:" }, { "from": "gpt", "value": "Location" } ]
[ { "from": "human", "value": "Detailed Instructions: Read the given query and classify it as a 'Good' or 'Bad' query depending on how well the query is formed, 'Bad' being the expected output for a not so well formed query and 'Good' being the expected output for a well formed query. A query may be wrong based on common sense or general facts, but if it is well formed, you should answer with Good.\nProblem:What will happens when you get tetanus ?\nSolution:" }, { "from": "gpt", "value": "Bad" } ]
[ { "from": "human", "value": "Given the prompt and a response, classify the them to \"yes\" if response is \"yes, and\" type. Otherwise classify it as \"no\". \"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). 1 In short, a \"Yes, and\" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'. \n\nPrompt: Last Blockbuster? Daddy-master, why didn't you tell us this before? \n Response: How are we going to trust you again? You withheld this information from us.\nyes\n\nPrompt: Claire, could you please ask Ralph what his department is? \n Response: I'm overseeing mostly. I'm in charge of operational duties throughout the day. The things that I'm under right now different umbrellas and what not, but my dad does own this particular Home Depot.\nyes\n\nPrompt: Alright, Pip, that's enough. Go have a seat. \n Response: That is true, but I also have a long beard and am frequently wet.\n" }, { "from": "gpt", "value": "no\n\n" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Given a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. For commands, 'left' and 'right' are used to denote the direction of an action. opposite turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. Actions and commands do not have quotations in the input and output.\n\nI_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK\n" }, { "from": "gpt", "value": "walk left thrice after look around left thrice" } ]
[ { "from": "human", "value": "In this task, you are given a statement spoken by a politician in natural language and the subject of the discussion for the given statement. Your task is to determine if the given subject of the discussion is correct for the given statement. The subject can be multiple words. Answer with \"True\" if it's the correct subject of discussion or return \"False\" if it's incorrect.\nQ: Statement: \"The money supply has doubled in the last year.\" \n Subject: labor,workers\nA: " }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "Definition: In this task, you need to provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are coarse labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e tagset of this corpus is - \n '.': Period symbol is used for symbols denoting Punctuations/Separations such as comma, period, backticks etc., \n 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, \n 'ADP': Adposition is a cover term for prepositions and postpositions, \n 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, \n 'CONJ': A word used to connect clauses or sentences or to coordinate words in the same clause, \n 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, \n 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, \n 'NUM': A numeral is a word, functioning most typically as a determiner, adjective or pronoun, that expresses a number and a relation to the number, such as quantity, sequence, frequency or fraction, \n 'PRT': Particles are function words that must be associated with another word or phrase to impart meaning and that do not satisfy definitions of other universal parts of speech, \n 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, \n 'PROPN': A proper noun is a noun (or nominal content word) that is the name (or part of the name) of a specific individual, place, or object, \n 'VERB': A verb is a member of the syntactic class of words that typically signal events and actions, can constitute a minimal predicate in a clause, and govern the number and types of other constituents which may occur in the clause, \n 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.\nInput: Sentence: `` I rather resent '' , she said , `` you speaking to {{ those }} groups in Portland as though just the move accomplished this . \nWord: those\nOutput:" }, { "from": "gpt", "value": "DET" } ]
[ { "from": "human", "value": "Part 1. Definition\nYou 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.\nPart 2. Example\nThe trophy doesn't fit into the brown suitcase because _ is too large.\nAnswer: trophy.\nExplanation: Answer is one of the objects (\"trophy\" and \"suitcase\") in the question. Since the blank is a \"large\" object that didn't fit the \"suitcase\", the answer must be \"trophy\".\nPart 3. Exercise\nJacob wanted his outside garden table to be plastic rather than wood, as the _ would warp with exposure to weather.\nAnswer:" }, { "from": "gpt", "value": "wood" } ]
[ { "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? Solve this instance: The event involving the player who topped the money list in 2002 moved to where in 1973 ?\nStudent:" }, { "from": "gpt", "value": "Tokyo Yomiuri Country Club" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the letters E, C, and N respectively.\nPart 2. Example\nSentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had been shopping for fruit to give Jon.\nAnswer: N\nExplanation: Tom's reason for buying the fruit is not known.\nPart 3. Exercise\nSentence 1: A man playing a bass on stage. Sentence 2: The man is playing jazz music.\nAnswer:" }, { "from": "gpt", "value": "N" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\nProblem:2, 8, ['j', '5445', '7091', 'w', '5509', 'G', '5235', 'T', 'W', '27', '6609', 'P', '1627']\nSolution:" }, { "from": "gpt", "value": "5445, 7091, w, 5509, G, 5235, T" } ]
[ { "from": "human", "value": "Definition: You are given a target race, and two sentences. Your task is to determine whether the second sentence is either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of people. An anti-stereotype is an idea that goes against the widely held but oversimplified notion of a group of people. Sentences and targets are unrelated if there is no relevance between them.\nInput: Target: Sierra Leon \nSierra Leone is in West Africa. Spaghetti is an Italian dish.\nOutput:" }, { "from": "gpt", "value": "unrelated" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task you are given a list of numbers and you need to find the average of each two consecutive values. The average of two numbers a and b is calculated as: (a + b) /2. The output should be a list of the averages of each two consecutive values. A list is presented with two brackets and comma-separated values, like: [1,2,3].\nQ: [-96, -42, -34, 57, -47, -54, 40, 97, 16, -76, -31, -24, 25, 81, -7]\nA:" }, { "from": "gpt", "value": "[-69.0, -38.0, 11.5, 5.0, -50.5, -7.0, 68.5, 56.5, -30.0, -53.5, -27.5, 0.5, 53.0, 37.0]" } ]
[ { "from": "human", "value": "Definition: In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about \"doctors\", you can talk about \"health\" or \"diagnosis\", but don't mention \"aliens\". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: \"She likes cakes.\" is changed to \"She doesn't like cakes.\"\nInput: Beginning: Last night my family and I decided to go to the new Italian restaurant Middle: The family ate lots of food. Ending: At least we had a coupon but we won't be back.\nOutput:" }, { "from": "gpt", "value": "It was the best dinner we had in years." } ]
[ { "from": "human", "value": "Teacher:You are given a passage. You need to construct a question about the information present in the passage. Construct a question in such a way that (i) it is unambiguous, (ii) its answer is the whole paragraph. Avoid creating questions that can be answered correctly without actually understanding the paragraph.\nTeacher: Now, understand the problem? Solve this instance: I heard garlic helps it lower. And OATMEAL!\nStudent:" }, { "from": "gpt", "value": "What is a good natural way to lower blood pressure?" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Given a set of four words, generate the category that the words belong to. Words are separated by commas. The possible categories are social gathering, accomodation, physical property, measurement unit, corporate, nutritional value, boats, police punishment, location (proximity), card games, outdoor sport activity, military rank, baby animals, weather, consumer product, animals, boxing terminology, food, chocolate food, bird, type of sandwich, date status, body part, ocean, employment activity, moral characteristic, elements, poker, computers, construction, guitar part, shady activities, physical activity, kitchenware, temperature, type of rigidity, emotional status, season, mode of transportation, window material, activity, emotional display, geographical property, fried food, store status, widespread, aesthetic characteristic, alcoholic drinks, secretary duty, direction, personal characteristic, and animal.\n\ncrane, tackle, neck, sandpiper\n" }, { "from": "gpt", "value": "bird" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to concatenate all elements of A from the ith element to the jth element, and print the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\nPROBLEM: 17, 22, ['h', '1221', '3491', '7041', 'm', '7999', 'V', 'r', 'D', 'r', '1121', 'N', '6441', '1683', '3653', 'U', 'e', 'L', '4859', '1677', 'U', '5549', 'g', '3859']\n\nSOLUTION: eL48591677U5549\n\nPROBLEM: 3, 14, ['J', '3163', 'y', 'o', 's', 'G', '3709', '7903', '3505', 'G', '6615', 'w', '6489', 'L', '1083', 'f', '5657', 'A', 'i', '1955', 'O', '4945', '1243', '5939', 'Q', 'D']\n\nSOLUTION: yosG370979033505G6615w6489L\n\nPROBLEM: 1, 15, ['n', '839', '4441', '1403', 'M', '5237', '7087', 'Q', 'P', 'V', '1225', 'Y', '4749', 'J', '6675', '4341', '2633', '9571', '4155', '7609', '9311', '1827', '441', '1421', 'O', '8767']\n\nSOLUTION:" }, { "from": "gpt", "value": "n83944411403M52377087QPV1225Y4749J6675\n\n" } ]
[ { "from": "human", "value": "In this task you will be given a list of strings and you need to concatenate them.\nOne example is below.\nQ: ['a', 'b', 'c']\nA: abc\nRationale: The strings 'a', 'b', 'c', got concatenated into the string 'abc'. So this is a good example.\nQ: ['stalked', 'Y', 'T', 'P', 'man', 'Q', 'among', 'c', 'V', 'n', 'K', 'M', 'z']\nA:" }, { "from": "gpt", "value": "stalkedYTPmanQamongcVnKMz" } ]
[ { "from": "human", "value": "Q: You are given a question title. You need to classify it into one of the 10 topics: 0 - 'Society & Culture', 1 - 'Science & Mathematics', 2 - 'Health', 3 - 'Education & Reference', 4 - 'Computers & Internet', 5 - 'Sports', 6 - 'Business & Finance', 7 - 'Entertainment & Music', 8 - 'Family & Relationships', 9 - 'Politics & Government'.\nwhy \"liberal\" in the US is considered as \"left\", while in europe is used to define a conservative?\nA:" }, { "from": "gpt", "value": "9" } ]
[ { "from": "human", "value": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input 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. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\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: rap. \nQuestion: James needed more sheet in writing down his rap lyric because the _ is long. \nAnswer: lyric." }, { "from": "gpt", "value": "James needed more sheet in writing down his rap lyric because the _ is short." } ]
[ { "from": "human", "value": "TASK DEFINITION: Given a question and its paraphrases, answer the question. The answer should exactly answer all the questions given without any ambiguity. Don't give partial answers.\nPROBLEM: Questions: ['at what age did napoleon die?']\n\nSOLUTION: 51 years\n\nPROBLEM: Questions: ['what date did portugal gain its independence', 'when does portugal celebrate its independence day?', 'what day is portugals independence day?', 'when did portugal acquire its independence?']\n\nSOLUTION: 1940-12-01\n\nPROBLEM: Questions: ['when did the english civil war start?']\n\nSOLUTION:" }, { "from": "gpt", "value": "1642-08-22\n\n" } ]
[ { "from": "human", "value": "Q: Given a sentence in English language, translate the sentence to Tagalog language keeping the meaning of the original sentence intact.\nEnglish sentence: If these are indeed as they appear we can say with certainty that Hipparchus was in Alexandria in 146 BC and in Rhodes near the end of his career in 127 BC and 126 BC.\nA:" }, { "from": "gpt", "value": "Kung ang mga ito ay katunayan na sila lalabas namin maaaring sabihin na may katiyakan na Hipparchus ay sa Alexandria sa 146 BC at sa Rhodes malapit sa katapusan ng kanyang karera sa 127 BC at 126 BC." } ]
[ { "from": "human", "value": "In this task, you're given an article, a question which often contains a blank, four options (associated with \"A\", \"B\", \"C\", \"D\") and the answer to that question. Your task is to classify whether the given answer is correct or not by providing \"Yes\" or \"No\", based on the article.\n\nLet me give you an example: Article: Homework can put you in a badmood , and that might actually be a good thing. Researchers from the University of Plymouth in England doubted whether mood might affect the way kids learn. To find out the answer, they did two experiments with children. The first experiment tested 30 kids. Someshapes were hidden inside a different, larger picture. The kids had to find the small shapes while sitting in a room with either cheerful or sad music playing in the background. To test their mood, the scientists asked the kids to point to one of five faces, from happy to sad. Children who listened to cheerful music tended to point to the smiley faces while the others pointed to the unhappy ones. The researchers found that sad kids took at least a second less to find the small shapes. They also found an average of three or four more shapes. In the second experiment, 61 children watched one of two scenes from a film. One scene was happy, and the other was sad. Just like in the first experiment, kids who saw the sad scene acted better compared to the others. The researchers guessed that feeling down makes people more likely to focus on a problem or difficult situation. Not all scientists agree with them, however. Other studies argued that maybe, that cheerful music in the first experiment distracted kids from finding shapes. While scientists work on finding out the answers, it still might be wise to choose when to do your tasks according to your mood. After eating a delicious ice cream, for example, write an essay. \n Question: Researchers did experiments on kids in order to find out _ . \n Options: (A) how they really feel when they are learning (B) whether mood affects their learning ability (C) what methods are easy for kids to learn (D) the relationship between sadness and happiness \n Answer: B\nThe answer to this example can be: Yes\nHere is why: It is clearly mentioned in the article that to the check effect of mood on children is the main purpose of the experiment. Hence, B is the correct answer and output is Yes.\n\nOK. solve this:\nArticle: My mother used to ask me what the most important part of the body is. Through the years Iwould take a guess at what I thought was the correct answer. When I was younger, I thought sound was very important to us as humans, so I said: \"My ears, Mommy.\" She said: \"No. Many people are deaf. But you keep thinking about it and I will ask you again soon.\"Several years passed before she asked me again. Since making my first attempt, I had contemplated the correct answer. So this time I told her: \"Mommy, sight is very important to everybody, so it must be our eyes.\" She looked at me and told me: \"You are learning fast, but the answer is not correct because there are many people who are blind.\" Mother asked me a couple more times and always her answer was \"No. But you are getting smarter every year, my child.\"Then last year, my grandpa died. Everybody was hurt. Everybody was crying. My momlooked at me when it was our turn to say our final goodbye to grandpa. She asked me: \"Do you know the most important body part yet, my dear?\" I was shocked when she asked me this now. She told me: \"This question is very important,especially at this moment. How you answer it can truly shows whether you have learned about life. For every body part you gave me in the past, I have told you were wrong and I have given you an example why. But today is the day you need to learn this important lesson.\" I saw her eyes well up with tears. She said: \"My dear, the most important body part is your shoulder.\"\"Is it because it holds up my head?\" I asked.\"No, it is because it can hold the head of a friend or a loved one when they cry,\" she replied:\"Everybody needs a shoulder to cry on somet ime in life, my dear. I only hope that you have enough love and friends that you will always have a shoulder to cry on when you need it.\" \n Question: The mother ask the question again after the grandfather died because _ . \n Options: (A) the answer was a way of honoring the grandfather. (B) at that moment, other body parts were less important. (C) the answer needed to be given to all members of the family. (D) at that moment the answer seemed especially true. \n Asnwer: D\nAnswer:" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "Teacher:You will be given a person's personality, and a history of a conversation this person has had. You will be given four candidate sentences to complete the conversation, based on the context. Choose one and answer with the text.\nTeacher: Now, understand the problem? Solve this instance: Personality: I drive a mercedes.\nI have a sweet tooth.\nI m the middle child of 3 siblings.\nI m a babysitter.\nI m getting married in six months.\nChat history: -Hello, how are you doing today?\n -I'm good. Just making my cat some warm milk. You?\nCandidates 1) I'm good! Does your cat like sweet stuff? 2) Oh wow that is impressive. Must be an extremely difficult job. 3) Good. I am glad to hear it. What kind of job are you looking for? 4) I am well just chatting with my friends trying to see where too this weekend.\nStudent:" }, { "from": "gpt", "value": "I'm good! Does your cat like sweet stuff?" } ]
[ { "from": "human", "value": "In this task you will be given a string of characters. You should remove all vowels from the given string. Vowels are: i,e,a,u,o. The character 'y' or 'Y' does not count as a vowel.\n\nUdVcUIQO\ndVcQ\n\nyHoDUh\nyHDh\n\nziJ\n" }, { "from": "gpt", "value": "zJ\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a sentence. You are expected to recognize the name of gene or protein. Although there might be several correct answers, you need to write one of them.\nQ: Following EGF or NGF stimulation of the v - CrkPC12 cells , the v - Crk protein itself became tyrosine phosphorylated within 1 min .\nA:" }, { "from": "gpt", "value": "v - Crk" } ]
[ { "from": "human", "value": "In this task, you will be shown an English sentence. You need to classify the sentence as either a representation of an adjunct island or as an incorrect representation. A correct representation should be denoted as 'good' while everything else should be denoted as 'bad'. A correct representation of an adjunct island will be a grammatically correct instance of a sentence using an adjunct island. An incorrect representation will be everything else.\nQ: Who will guys think about after praising Raymond?\nA: " }, { "from": "gpt", "value": "good" } ]
[ { "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 sentence or phrase in Xhosa. You must translate it to English in a way that is equivalent in terms of meaning and grammatically correct.\n\nUkuhla koxinzelelo lomoya qho kuyenzeka, imixokelelwano enoxinzelelo olusezantsi, ngomahluko wamaqondo obushushu omkhulu, iingqimba zomoya oshushu nobandayo.\nOutput:" }, { "from": "gpt", "value": "A depression is formed, or Low Pressure system, by large temperature differences between warm and cold air masses." } ]
[ { "from": "human", "value": "In this task, you're given a context passage, an answer, and a question. Your task is to classify whether the question for this answer is correct or not, based on the given context with commonsense reasoning about social situations. If its correct ,return \"True\" else \"False\".\n\nQ: Context: Quinn grabbed Lee by the shoulders and tried to surprise him. \n Answer: scared \n Question: How would Lee feel as a result?\n\nA: True\n**\nQ: Context: Bailey rounded the corner looking to score the winning run in baseball. \n Answer: accomplished \n Question: How would Bailey feel afterwards?\n\nA: True\n\nQ: Context: Taylor tore Addison's eyes away from the tv screen when the grizzly murder occured. \n Answer: be horrified \n Question: What will happen to Addison?\n\nA:" }, { "from": "gpt", "value": "True\n**\n" } ]
[ { "from": "human", "value": "In this task, find the most appropriate number to replace the blank (indicated with _ ) and express it in words.\n\nExample Input: World population continues to rise, even as a few countries move toward _ growth.\nExample Output: zero\n\nExample Input: Autism is _ to four times more likely to affect boys than girls.\nExample Output: three\n\nExample Input: Most spiders have eight eyes, but the brown recluse has _ eyes arranged in a distinctive pattern.\nExample Output:" }, { "from": "gpt", "value": "six\n\n" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. 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\nWhen did the us leave the vietnam war?\n" }, { "from": "gpt", "value": "When did the us troop presence in Vietnam peak during the vietnam war? \n 1968" } ]
[ { "from": "human", "value": "You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. You are required to assign a label 'formal' if there is an absence of emotion and a presence of questions anywhere within the conversation. If such pattern is not found assign the label 'informal'.\nQ: Person1: Hey , This is your order . \n Person2:Are you new here ? I come to this coffeehouse often . But I didn't see you here before . \n Person1: Yes . I started this part-time job just three days ago . And my internship will last 1 week . I'm still a student now . \n Person2:Do you mind if I ask you why you've taken the part-time job here ? \n Person1: Of course not . You know , there are many foreign customers like you here . And I think it's good for me to improve my oral English . \n Person2:Oh , are you an English student ? Or you just study English for interest's sake ? \n Person1: No , I'm not an English student . But I do like English . I'm going to be a volunteer in the 2008 Olympics where I want to be helpful with the language . So I try to improve my English . \n Person2:Very nice . Thank you for your time . \n Person1: Thank you , sir . But I'm not allowed to accept any tips . \n Person2:OK then . I don't want to put you in trouble . \n Person1: Well , would you like something else ? The new-made cafe parfait is really good . Want some ? \n Person2:OK . But I'd like some cookies . \n Person1: Sure . If you want more coffee , please go over there . There is self-help coffee maker . \n Person2:I surely know that . Don't forget that I am a regular customer here . \n Person1: Oops . Well , wait for a while . We'll get it done quickly . \n Person2:It's OK . Thank you . \nA: " }, { "from": "gpt", "value": "informal" } ]
[ { "from": "human", "value": "Instructions: Two analogies that relate items to whether they are trash or treasure is given in the form \"A : B. C : ?\". Items marked as \"trash\" are considered to not have value and can be disposed, whereas those marked as \"treasure\" are considered valuable items that must be retained. \"A : \"B relates item A to whether it is trash or treasure, as specified by B. Your task is to replace the question mark (?) with either `trash` or `treasure` for the given item C, following the \"A : B\" relation.\nInput: wallet : treasure. computer : ?\nOutput:" }, { "from": "gpt", "value": "treasure" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given an input list A comprising of numbers and alphabets. You need to extract and sort the unique alphabets in the list. The alphabets in the input list will only be in lowercase. Return -1 if there is no alphabet in the input list.\nProblem:['6437', '2739', '8419']\nSolution:" }, { "from": "gpt", "value": "-1" } ]
[ { "from": "human", "value": "Read the given query and classify it as a 'Good' or 'Bad' query depending on how well the query is formed, 'Bad' being the expected output for a not so well formed query and 'Good' being the expected output for a well formed query. A query may be wrong based on common sense or general facts, but if it is well formed, you should answer with Good.\n\nEx Input:\nWhich of the following is an important reason why Wegener 's continental drift hypothesis was not widely accepted ?\n\nEx Output:\nGood\n\n\nEx Input:\nWhat is coefficient of emmission for perfectly black body ?\n\nEx Output:\nBad\n\n\nEx Input:\nAre pythens omnivore ?\n\nEx Output:\n" }, { "from": "gpt", "value": "Bad\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to concatenate all elements of A from the ith element to the jth element, and print the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\nSee one example below:\nProblem: 6, 14, ['9545', '5185', '1667', 'w', 's', '9559', 'T', 'u', 'U', '6843', 'L', 'l', '6365', '7103', 'A', '2381', '5037', 'X', '4487', 'd']\nSolution: 9559TuU6843Ll63657103\nExplanation: Here, concatenating all the elements between the 6th element and 14th element gives '9559TuU6843Ll63657103'.\n\nProblem: 5, 6, ['E', 'W', 'M', '497', 'h', '7955', '1433', '43', '2193']\nSolution:" }, { "from": "gpt", "value": "h7955" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: insult and non-insult. Insult is any lanugage or act that is disrespectful or scornfully abusive.\nPROBLEM: Comment: Agree that Bannon's pushing to get out of the Paris Accord was a terrible move.\n\n\"Climate Change\" is the closest thing there is to a world religion. Even the DPRK has signed on to the Paris Accord, not of course, that it really affects them in any material way.\n\nGiving notice to withdraw from the Paris Accord has been a complete disaster with respect to the allies we desperately need during this extremely perilous time. The U.K., France, and Germany are good examples of this.\n\nTrump should have simply smiled and pursued the tact that Xi & Modi have -- i.e. tacit agreement but still acting in their nation's best interest.\n\nSince Bannon helped to orchestrate Trump's upset win he's certainly not an \"idiot\" with respect to grass roots politics. He might well be deemed an \"idiot\" for the disastrous effect his climate change stance has had on our geo-political security.\n\nDo you have any specific examples which prove that Bannon is a \"racist?\"\n\nThanks.\n\nSOLUTION: Insult\n\nPROBLEM: Comment: you Steve are full of stupid as usual !,, trump is a leader making real change for the usa, already progress and he hasnt even been sworn in yeT!... aa the left keep crying as trump and co. dismantle all the bs regulations and taxes that you take out of society!!!! its ignorance by fools like you that are childish and just stupid\n\nSOLUTION: Insult\n\nPROBLEM: Comment: Freedom of speech is not the same thing as freedom from consequence. Besides it's Google's discretion to remove any employee they seem unfit for their corporate vision. You also had other engineers threatening to quit or retaliate if something wasn't done. Plenty of diverse opinion is allowed at Google, but not all opinions are equal nor good for the company. For example someone writing a \"manifesto\" about \"the killing the Jews\" should also be fired.\n\nSOLUTION:" }, { "from": "gpt", "value": "Non-insult\n\n" } ]
[ { "from": "human", "value": "In this task, you will be presented with a question having multiple possible answers in Swahili language. And you should choose a most suitable option out of \"A\", \"B\", \"C\", \"D\", and \"E\" based on your commonsense knowledge.\n\n[EX Q]: Question: Uko wapi ikiwa idadi ya wanariadha wanapambana? \n Options: A michubuko B Ugiriki ya kale C mashindano D kupata bure E mafanikio \n[EX A]: C\n\n[EX Q]: Question: Je! Kalamu ya mpira inaweza kuwa na faida gani kwa kuandika hundi? \n Options: A nyumbani B mkoba C dawati la ofisi D Benki E Droo ya dawati \n[EX A]: D\n\n[EX Q]: Question: Unaweza kuhifadhi wapi kitabu ambacho hutahitaji kwa muda karibu na kitambaa unachovaa? \n Options: A maktaba ya mkutano B dawati C chumbani D darasa E rafu ya vitabu \n[EX A]:" }, { "from": "gpt", "value": "C\n\n" } ]
[ { "from": "human", "value": "In this task you will be given an arithmetic operation and you have to find its answer. The symbols of operators '+' and '-' has been swapped i.e you need to perform subtraction when you see a '+' symbol and addition in case of '-' symbol.\nOne example: 5 + 3\nSolution is here: 2\nExplanation: Here, '+' represents subtraction operation. So, the answer is 2 (5-3=2).\n\nNow, solve this: 4685 - 3751 - 5266 + 2023 - 1398 + 9926 - 5442 + 9160 - 6231\nSolution:" }, { "from": "gpt", "value": "5664" } ]
[ { "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 = 8, equation weights = [1, 6, 0]\nOutput:" }, { "from": "gpt", "value": "112" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task you will be given a list of integers. You should find the maximum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one integer subtracted by another. The output should be a single integer which is the largest possible absolute distance.\nSee one example below:\nProblem: [73, 30, 71, 47, -65, 50, -90, -60]\nSolution: 163\nExplanation: The maximum absolute difference is 163 because '\|-90 - 73\| = 163' which is the maximum possible absolute difference. So this is a good example.\n\nProblem: [91, -63, 65, 97, -57, -15, -28, -11, -84]\nSolution:" }, { "from": "gpt", "value": "181" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you will be presented with a context from an academic paper and a question based on the context. You have to classify the questions into \"Extractive\", \"Abstractive\", or \"Yes-no\" questions. Extractive questions can be answered by concatenating extracts taken from a context into a summary while answering abstractive questions involves paraphrasing the context using novel sentences. Yes-no question is a question whose expected answer is one of two choices, one that affirms the question and one that denies the question. Typically, the choices are either yes or no.\nQ: Moreover, because English does not mark grammatical gender, approaches developed for English are not transferable to morphologically rich languages that exhibit gender agreement BIBREF8 . \n Question: Why does not the approach from English work on other languages?\nA:" }, { "from": "gpt", "value": "Abstractive" } ]

Subsets and Splits

No community queries yet

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