Datasets:

Alignment-Lab-AI

/

english-flan

like 0

[ { "from": "human", "value": "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.\n\nSentence: Telerate 's two independent directors have rejected the offer {{ as }} inadequate . \nWord: as\nADP\n\nSentence: The thrift said that `` after these charges and * assuming no dramatic fluctuation in interest rates {{ , }} the association expects *-1 to achieve near record earnings in 1990 . '' \nWord: ,\n.\n\nSentence: January platinum was down $ 5.70 *U* {{ an }} ounce at $ 494.50 *U* . \nWord: an\n" }, { "from": "gpt", "value": "DET\n\n" } ]

[ { "from": "human", "value": "Teacher: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.\nTeacher: Now, understand the problem? Solve this instance: 9301 + 1619 - 7459 + 5871 + 2497 + 4093 + 7957 - 1085 - 6698\nStudent:" }, { "from": "gpt", "value": "2506" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you are given inputs 'i', 'j', and A, where 'i' and 'j' are integers and A is a list. A list is shown by two brackets and comma-separated numbers and characters inside, like ['1', '12', 'l']. You need to concatenate all elements of A from the ith element to the jth element, and then reverse the resulting string. 'i' and 'j' will be non-negative, and will always have a value less than the length of A. 'i' will always be less than 'j'. Perform the operations in order, i.e., do not reverse first and then concatenate.\nProblem:10, 27, ['407', 'b', 's', '3171', '8461', '4681', '5237', 't', '5871', '447', 'S', 'c', 'd', '1421', '3011', '821', '8683', '3203', '2079', 'N', 'F', 'E', 'H', '8773', '2259', 'K', 'f']\nSolution:" }, { "from": "gpt", "value": "fK95223778HEFN97023023386812811031241dcS744" } ]

[ { "from": "human", "value": "Teacher:In this task you will be given a list of lists, of numbers. For every inner list, you should multiply every number in that list and put the results in your answer. The output should be a list of numbers with the same length as the number of the lists in the input list.\nTeacher: Now, understand the problem? Solve this instance: [[-39, 42, -3], [31, -20], [-40, -33, -5, 49], [-24, 39, 2, -19], [-44, 47, -11, 20], [50, 7]]\nStudent:" }, { "from": "gpt", "value": "[4914, -620, -323400, 35568, 454960, 350]" } ]

[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you're given the title of a five-sentence story, the first four sentences, and two options for the fifth sentence as a and b. Your job is to pick the sentence option that does not connect with the rest of the story, indicating your choice as 'a' or 'b'. If both sentences are plausible, pick the one that makes less sense.\n\nTitle: Found wallet. Sentence 1: Kelly was walking into the grocery store. Sentence 2: On her way there, she saw a wallet on the ground. Sentence 3: She immediately picked it up and looked inside. Sentence 4: As soon as she found who it was, she took it into the store. Choices: a. She hoped the store would help find the owner. b. Thankfully people came right away.\n" }, { "from": "gpt", "value": "b" } ]

[ { "from": "human", "value": "Detailed Instructions: Given two noun phrases (arguments) and relationship between them, form a sentence that expresses theses arguments with the given relationship.\nProblem:Relationship: 'be country in', Argument/Subject 1: 'hungary', Argument/Subject 2: 'europe'\nSolution:" }, { "from": "gpt", "value": "I also traveled to many other countries in Western Europe , including four trips to Eastern European countries , such as the Czech Republic , former East Germany , Hungary , the Ukraine and Yugoslavia ." } ]

[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nYou are provided with an \"Event\" and it's \"Intent\" related to PersonX. Determine the sentiment value of the given input as either \"Positive\", \"Negative\", and \"Unknown\". \n\nEvent:PersonX keeps driving. Intent: 1) to finish their homework\nOutput:" }, { "from": "gpt", "value": "Negative" } ]

[ { "from": "human", "value": "Q: The task is to generate text based off of an event. For the given event, there will be a person who does the action in the event (usually PersonX). Your task is to write that persons intent behind doing the event, i.e. why did the person do that action.\nPersonX gets home from school\nA:" }, { "from": "gpt", "value": "to rest" } ]

[ { "from": "human", "value": "Definition: In this task you will be given some text dialogue and you need to infer the underlying emotion of the text. The possible emotions are happy, sad, angry, or other.\nInput: yes i am very enerjetic you are indeed yes i am missing\nOutput:" }, { "from": "gpt", "value": "sad" } ]

[ { "from": "human", "value": "In this task, you are given inputs 'i', 'j', and A, where 'i' and 'j' are integers and A is a list. A list is shown by two brackets and comma-separated numbers and characters inside, like ['1', '12', 'l']. You need to concatenate all elements of A from the ith element to the jth element, and then reverse the resulting string. 'i' and 'j' will be non-negative, and will always have a value less than the length of A. 'i' will always be less than 'j'. Perform the operations in order, i.e., do not reverse first and then concatenate.\nExample: 1, 3, ['238', 'h', '92', 'U', '2799']\nExample solution: 29h832\nExample explanation: Here, concatenating all the elements between the 1st element and 3rd element and then reversing the string gives '29h832'.\n\nProblem: 5, 8, ['9353', '7105', 'm', 'q', '745', 'H', 'V', 'E', 'i', '6295', '6879', '9843', '4503', '3395', '9497', 'b', '7175', 'Y', '585', '9437', '7021', 'x']\n" }, { "from": "gpt", "value": "Solution: EVH547" } ]

[ { "from": "human", "value": "Part 1. Definition\nIn 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.\nPart 2. Example\n['8129', 'a', '4245', 'y', 'm', 'a']\nAnswer: a, m, y\nExplanation: Here, the unique alphabets in the list are 'a', 'y', and 'm', hence their sorted order is 'a, m, y'.\nPart 3. Exercise\n['6437', '2739', '8419']\nAnswer:" }, { "from": "gpt", "value": "-1" } ]

[ { "from": "human", "value": "Teacher: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.\nTeacher: Now, understand the problem? Solve this instance: Chemotherapy is given intervenously every ____ to four weeks as tolerated for at least six cycles.\nStudent:" }, { "from": "gpt", "value": "three" } ]

[ { "from": "human", "value": "Detailed Instructions: In 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.\nQ: Le yayingazi kuba njengoku'Ngxama' okwakusele kukwisibini sesithathu sondoqo wenguqu ezantshintshela kwekhawulezayo inqanawa evulelwe umoya .\nA:" }, { "from": "gpt", "value": "This was not to be as the Furious was already in the second of three major alterations that changed her into a fleet aircraft carrier." } ]

[ { "from": "human", "value": "Given a sentence in English language, translate the sentence to Tagalog language keeping the meaning of the original sentence intact.\n\nEnglish sentence: Also while Porphyry was in Sicily, he wrote a work on vegetarianism and a critical work against Christian doctrines." }, { "from": "gpt", "value": "Din habang porpiri ay sa Sisilya, he wrote isang trabaho sa vegetarianism at isang kritikal na gawain laban sa Christian doktrina." } ]

[ { "from": "human", "value": "Detailed Instructions: Here are two questions (Question1 and Question2). If these questions have the same meaning and same answer, answer \"Yes\", otherwise \"No\".\nProblem:Question1: How cloud computing works?, Question2: What is Work of Cloud computing Engineers?\nSolution:" }, { "from": "gpt", "value": "No" } ]

[ { "from": "human", "value": "Instructions: Given a sentence and two mentions from the text (arguments), indicate a phrase (a verb or noun phrase) that describes the relationship between the provided arguments.\nInput: Sentence: 'Arab-Israeli Conflict : The leaders of the Gulf Co-operation Council urge US President George W. Bush to make the creation of an independent Palestinian state an absolute priority at their annual meeting , which is being held in Bahrain .', Argument/Subject 1: 'council', Argument/Subject 2: 'president'\nOutput:" }, { "from": "gpt", "value": "be make up of" } ]

[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nYou're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"sympathetic\" to \"stern\"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them.\n\nContext Word: New Hampshire. \nQuestion: In New Hampshire PersonX has been detained for shoplifting by PersonY, _ is a thief. \nAnswer: PersonX\nOutput:" }, { "from": "gpt", "value": "In New Hampshire PersonX has been detained for shoplifting by PersonY, _ is a under cover cop." } ]

[ { "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 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'.\n\nQuery: Tell me about defender \n Clarification: are you referring to the arcade game called defender\nSolution: Yes\nWhy? The given clarification properly clarify the query. Hence, the output is Yes.\n\nNew input: Query: Tell me about the pacific northwest laboratory. \n Clarification: do you want to watch funny penguin videos\nSolution:" }, { "from": "gpt", "value": "No" } ]

[ { "from": "human", "value": "Detailed Instructions: Languages typically provide more than one grammatical construction to express certain types of messages. Your task is to generate a senetence with the same meaning as given sentence, but with different grammatical construction.\nSee one example below:\nProblem: Bob took the woman from work a cake\nSolution: Bob took a cake to the woman from work\nExplanation: Input and output sentences have same meaning but different grammatical construction.\n\nProblem: Mary leased the woman something\nSolution:" }, { "from": "gpt", "value": "Mary leased something to the woman" } ]

[ { "from": "human", "value": "In this task you will be given a list of numbers and you should remove all duplicates in the list. If every number is repeated in the list an empty list should be returned. Your list should be numbers inside brackets, just like the given list.\nOne example is below.\nQ: [0,1,0,2,5,1]\nA: [2,5]\nRationale: The only elements that are not duplicated is 2 and 5. This is a good example.\nQ: [2, 1, 3, 1, 3, 0, 2, 4, 4]\nA:" }, { "from": "gpt", "value": "[0]" } ]

[ { "from": "human", "value": "Detailed Instructions: In 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.\nQ: Yi-arhente enoxanduva lokuqinisekisa ukuba i-V&V iyenziwa kwimodeli echaziweyo okanye kwimfaniso. [DIS]\nA:" }, { "from": "gpt", "value": "The agency responsible for ensuring V&V is performed on a specific model or simulation. [DIS]" } ]

[ { "from": "human", "value": "In this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n\n[Q]: select the rows whose high rebounds record fuzzily matches to tim duncan . the average of the high rebounds record of these rows is 11.5 .\n[A]: round_eq { avg { filter_eq { all_rows ; high rebounds ; tim duncan } ; high rebounds } ; 11.5 }\n\n\n[Q]: for the notes records of all rows , all of them fuzzily match to high jump .\n[A]: all_eq { all_rows ; notes ; high jump }\n\n\n[Q]: the sum of the crowd record of all rows is 79,000 .\n[A]:" }, { "from": "gpt", "value": "round_eq { sum { all_rows ; crowd } ; 79,000 }\n\n\n" } ]

[ { "from": "human", "value": "Instructions: You are given a science question (hard-level) and four answer options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer based on scientific facts, knowledge, and reasoning. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D'. There is only one correct answer for each question.\nInput: Which of the following would you most likely use to study the growth of an insect over time? \n (A) a clock that measures seconds (B) a hand lens with a large lens (C) several insects that feed on other insects (D) a glass aquarium with food for the insect\nOutput:" }, { "from": "gpt", "value": "D" } ]

[ { "from": "human", "value": "In this task, you are given a sentence. You must judge whether a single noun or verb has been replaced with another word with the same part of speech. The inversion would result in the sentence sounding unnatural, So unnatural sentences will be considered changed. Label the instances as \"Original\" or \"Changed\" based on your judgment.\n\nInput: Consider Input: It just seemed much more fun when all the bystanders participated .\n\nOutput: Changed\n\n\nInput: Consider Input: He was camouflaged so well , Neil hardly noticed him .\n\nOutput: Original\n\n\nInput: Consider Input: I am a banker and I appreciate the theory on principal and interest as we are trained to keep an eye primarily on interest earned .\n\n" }, { "from": "gpt", "value": "Output: Original\n\n\n" } ]

[ { "from": "human", "value": "In this task, you are given a word. You should respond with a valid sentence which contains the given word. Make sure that the sentence is grammatically correct. You may use the word in a different tense than is given. For example, you may use the word 'ended' in the output where the given input word is 'end'.\n\nQ: exhaust\n\nA: Exhaust one's savings.\n****\nQ: flap\n\nA: He wrote on the flap of the envelope.\n****\nQ: enter\n\nA:" }, { "from": "gpt", "value": "Enter a race.\n****\n" } ]

[ { "from": "human", "value": "Given the task definition and input, reply with output. Write an incorrect answer to the given question based on the associated fact. You are also provided with the correct answer to the given question. Make sure that your incorrect answer is relevant and similar to the associated fact. Also, try to make the incorrect answer similar to the correct answer so that distinguishing the correct answer from the incorrect answer is not very easy. Make sure you don't accidentally provide another correct answer! Also, make sure they sound reasonable (e.g., might be on a school pop quiz). A good incorrect answer can be constructed using words associated with the question, but not the correct answer. For example, for the question \"What helps plants survive?\", using words like \"weeds\", \"vase\", \"bee\" (associated with \"plant\"), or \"first aid\", \"parachute\", \"accident\" (associated with \"survive\") etc. Your incorrect answers make the question hard, so these results in good incorrect answers.\n\nFact: most streams start with precipitation. \nQuestion: What do most streams start with? \nCorrect Answer: precipitation.\n" }, { "from": "gpt", "value": "heat." } ]

[ { "from": "human", "value": "Instructions: Given a post that is a real-life anecdote of a complex ethical situation and a question asks if AUTHOR, NOBODY, EVERYBODY, or OTHER is wrong in the situation. Answer the question and classify your answers into yes or no.\nInput: Is AUTHOR wrong in the post ? POST : My sister is worried about my moms smoking habit.She wants to stage an intervention. My mom lost a lot weight recently. I told her look she's 55 and independent we can't force her. We are in our late 20's and I told her and intervention would not even work if we were children. I have tried in the past and even bought her a vape. She asked me if I even care. I told her not really and she asks if I would be sad if something happens to her.. I said I wouldn't be surprised if she had issues due to her smoking. She was upset and claimed I don't care if they died. I told her I mentally prepared myself for the death of our parents a long time ago because they really don't take care of themselves at all. She said I sound like a sociopath and started crying.. I told her I care about her and her well being but she was just so mad but honestly they are not that old where I have to take care of them tbh. It probbaly does not help my relationship with my mom is not that great. \nOutput:" }, { "from": "gpt", "value": "no" } ]

[ { "from": "human", "value": "Teacher: Craft one incorrect answer. In doing so, try to use words from the context as much as possible, or by using similar words used in the correct answer. DO NOT craft nonsensical or off-topic incorrect answers, such that the incorrect answers can be directly excluded without reasoning according to the context. Try to make your responses similar to the given correct answer. To this end, try to keep both the length and the style as similar as possible between the correct and the incorrect answer. To make your incorrect answers more difficult, try to incorporate words from context. To avoid being predictable or repetitive, try to add more variations and complexity.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nContext: I was told, in person over the phone, that my shoes were on their way. They have my money. I have no shoes. \nQuestion: What may happen before I called them? \nCorrect answer: I found the money was charged but I have not got shoes.\nSolution: I found the shoes were still on the way after several days.\nReason: Excellent incorrect answer: as it includes topically relevant words while still being incorrect.\n\nNow, solve this instance: Context: i had a dream that me and my family ( in this dream there were more kids for some reason ) we lived on some sort of farm , and there was supposedly a special \" visitor \" coming to see us . When the visitor pulled up in his truck i was instantly scared , he was red with horns and glowing eyes- it was SATAN ! ! ! - in redneck form . Anyways , he 'd get out his truck and play with us , he was friendly ; until he found out that his wife was cheating on him , then he got mad . \nQuestion: Why is the event being discussed so unusual? \nCorrect Answer: The speaker has a creative imagination.\nStudent:" }, { "from": "gpt", "value": "The speak is remember his strangest event." } ]

[ { "from": "human", "value": "Generate a correct and concise answer for the question based on the words in the context.\nQ: Context : ISO 3166-2:MN is the entry for Mongolia in ISO 3166-2, part of the ISO 3166 standard published by the International Organization for Standardization (ISO), which defines codes for the names of the principal subdivisions (e.g., provinces or states) of all countries coded in ISO 3166-1. \nQuestion : Who set the standards for ISO 3166-2:MN?\nA: " }, { "from": "gpt", "value": "International Organization for Standardization" } ]

[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGiven a comment text in Tamil, classify the comment into one of these categories (i) Hope speech, if it contains encouraging, positive or supportive contents about equality, diversity or inclusion, (ii) Not Hope Speech or (iii) Not in Expected Language, if the text is not Tamil.\n\nMadan gowri fans like here\nOutput:" }, { "from": "gpt", "value": "Not in Expected Language" } ]

[ { "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 commands (in terms of logical operations) and natural interpretation of the given command to select relevant rows from the given table. Your job is to generate a label \"yes\" if the interpretation is appropriate for the command, otherwise generate label \"no\". \n Here are the definitions of logical operators: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n\nCommand: eq { count { filter_eq { all_rows ; surface ; grass } } ; 2 }, interpretation: select the row whose gdp per capita ( us ) record of all rows is maximum . the member countries record of this row is austria .\nOutput:" }, { "from": "gpt", "value": "no" } ]

[ { "from": "human", "value": "Instructions: From the given sentence, extract the phrase (often noun or verb) that carries the given relationship. The generated phrase should be present in the sentence.\nInput: Given Relationship: 'be home to', Sentence: 'Mumbai is the home of Bollywood movies which entertain the world .'\nOutput:" }, { "from": "gpt", "value": "home" } ]

[ { "from": "human", "value": "In this task, you are given a statement spoken by a politician in natural language. Your task is to generate the subject of the discussion for the given statement. The subject generated is not necessarily a part of the given input. Your answer should contain one or more words.\n\nLet me give you an example: Says the Annies List political group supports third-trimester abortions on demand.\nThe answer to this example can be: abortion\nHere is why: It's a correct subject of the statement because it talks about a political group supporting demans of abortions.\n\nOK. solve this:\nTeachers are working their third consecutive year -- some longer than that -- without salary increases.\nAnswer:" }, { "from": "gpt", "value": "education" } ]

[ { "from": "human", "value": "Detailed Instructions: \"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...\"). Given a prompt and two responses, identify which response is the type of \"yes, and\". Indicate your answer by 'Response 1' if the first response is correct, otherwise 'Response 2'. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange.\nQ: Prompt: I was busy installing moss where you asked me to install moss. \n Response 1: Yes, everyone has a job. We're not keeping track of your daughter everywhere we go. Be a real dad, you know? \n Response 2: Mitch, I woke up thinking cubes. I didn't know why. I had a premonition - a cube-onition.\nA:" }, { "from": "gpt", "value": "Response 1" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a conversation between a flight agent and the customer. You are given 4 options and you need to select the goal of the conversation. It is provided as part of customer's context, which has to be one of the following: `book`: Make a new reservation, `cancel`: Cancel an existing reservation, `no_flight`: No flight found for the customer's preference, `no_reservation`: No reservation / No change / No cancellation was made in the conversation, mostly enquiring details\nQ: customer: Hello. \n agent: Hello, how may I aid you today from my end? \n customer: Stephen Hernandez here. I am looking a flight from BOS to SEA, can you help me? \n agent: Sure, I am here to help you out. Please provide me your trip dates. \n customer: My planning dates are 03/16 and 03/18. \n agent: Please wait a moment. \n customer: Sure. \n agent: Here is a flight with 2 stops and airfare is 100 in 1002 Spirit airlines, can I proceed with it? \n customer: I need a direct flight. \n agent: Let me check with your request. \n customer: Ok, take your own time. \n agent: Sorry Stephen, there is no direct flight with your travel dates in your route. \n customer: It's ok, thank you for checking. \n agent: Thank you for reaching us.\nA:" }, { "from": "gpt", "value": "no_flight" } ]

[ { "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 two questions. You should decide whether the second question is a good paraphrase of the first one. If you are able to tell that the two questions are the same without any other information, answer \"Yes\", otherwise answer \"No\".\n\noriginal question: Which class of computer peripheral supports [Pyjamarama]?\nparaphrase: [Pyjamarama] is supported by which class of computer peripheral?\nSolution: Yes\nWhy? The second question is a good paraphrase of the first question and they have the same answer.\n\nNew input: original question: What adaptation is adapted from [Via Mala]\nparaphrase: What novel by the Swiss writer John Knittel is an adaptation of [Via Mala]?\nSolution:" }, { "from": "gpt", "value": "Yes" } ]

[ { "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 are given an open-domain question from an open movie database. Your task is to provide an answer to that question. Try to only include the answer. Do not put it in a sentence.\n\nwhat kind of film is Best Seller?\nSolution: crime\nWhy? The answer is correct because crime genre movie is among best seller.\n\nNew input: what films did Toshiyuki Nishida star in?\nSolution:" }, { "from": "gpt", "value": "Emperor, The Ramen Girl, Beyond Outrage, A Letter to Momo" } ]

[ { "from": "human", "value": "Detailed Instructions: Given a comment text in Tamil, classify the comment into one of these categories (i) Hope speech, if it contains encouraging, positive or supportive contents about equality, diversity or inclusion, (ii) Not Hope Speech or (iii) Not in Expected Language, if the text is not Tamil.\nSee one example below:\nProblem: Spr Ithan sariyana valli\nSolution: Hope Speech\nExplanation: The given text contains content that is encouraging, positive or supportive contents and talks about equality, diversity or inclusion and is in expected language - tamil\n\nProblem: Nenga enna phone use panrenga bro\nSolution:" }, { "from": "gpt", "value": "Hope Speech" } ]

[ { "from": "human", "value": "In this task, you are given a question. Your task is to generate an answer that is relevant to the question.\nOne example: Are you willing to do shopping with me?\nSolution is here: I only like to shop during festivals\nExplanation: Based on the given question and answer, the dialogue is about shopping, so the question and answer are relevant.\n\nNow, solve this: Do you like going out?\nSolution:" }, { "from": "gpt", "value": "Depends on where I'm going." } ]

[ { "from": "human", "value": "Instructions: You are given a short text as a title. Your task is to generate a poem as output that is related to the given title and should feel like written by kids. The output should be a run-on sentence (two or more complete sentences connected without any punctuation). The poem should not be too long or too complex, because it should feel like it is written by younger person without high level of literature education.\nInput: ''I'm a Crotchety Witch''\nOutput:" }, { "from": "gpt", "value": "i'm a crotchety witch live all by myself i have n't one crony not ogre nor elf no wizard or warlock drop by for a stay hobgoblins avoid me- i like it that way my room be suffuse with perennial gloom i never go out i've retire my broom i do n't even bother to boil a few brew so i'm not to blame if there's ooze in your shoe today be my b-day i bake a stale cake instead of a candle i stick in a snake i've turn 30303 the snake get away- happy b-day to me" } ]

[ { "from": "human", "value": "Part 1. Definition\nIn this task, you are given an answer, and your task is to generate a reasonable question for that answer.\nPart 2. Example\nMy stomach will be upset if i eat that.\nAnswer: Do you like pineapple on your pizza?\nExplanation: The answer given was regarding something that the person ate and it caused his stomach upset. The question asked was if that person likes pineapple on pizza. Based on the given answer, the question was predicted correctly.\nPart 3. Exercise\nLong and epic tales pique my interest.\nAnswer:" }, { "from": "gpt", "value": "Are long books your thing?" } ]

[ { "from": "human", "value": "Definition: In this task, you are given a summary for US Congressional and California state bill, your task is to generate a Title for this bill. The preferred titles are under forty words and mention the purpose of the bill.\nInput: Mount St. Helens National Volcanic Monument Completion Act - Requires the Secretary of the Interior to acquire, by exchange, the mineral and geothermal interests of each company (Burlington Northern, Incorporated or the Weyerhaeuser Company) in the Mount St. Helens National Volcanic Monument in the State of Washington. \nSets forth requirements and administrative procedures for such exchange, including requiring the Secretary, in exchange for all mineral and geothermal interests acquired from each company, to issue to each such company monetary credits with a value of $2.1 million that may be used for the payment of: (1) not more than 50 percent of the bonus or other payments made by successful bidders in any sales of mineral, oil, gas, or geothermal leases under the Mineral Leasing Act, the Outer Continental Shelf Lands Act, or the Geothermal Steam Act of 1970 in the contiguous 48 States; (2) not more than ten percent of the bonus or other payments made by successful bidders in any sales of such leases under such Acts; (3) not more than 50 percent of any royalty, rental, or advance royalty payment made to the United States to maintain any mineral, oil, or gas, or geothermal lease in the 48 contiguous States issued under such Acts; or (4) not more than ten percent of any royalty, rental, or advance royalty payment made to the United States to maintain any mineral, oil, or gas, or geothermal lease in Alaska issued under such Acts. Requires the Secretary to accept credits in the same manner as cash for the payments. Requires that all amounts in the form of credits accepted by the Secretary for the payments be considered to be money received for the purpose of the Mineral Leasing Act and the Geothermal Steam Act of 1970. \nDirects the Secretary, not later than 30 days after the completion of the required exchange with a company, to establish an exchange account for that company for the monetary credits issued to it. Permits: (1) a company to transfer or sell any credits in the company's account to another person; and (2) such credits transferred or sold to be used only by a person that is qualified to bid on, or that holds, a mineral, oil, or gas lease under the Mineral Leasing Act, the Outer Continental Shelf Lands Act, or the Geothermal Steam Act of 1970. Terminates an account created for a company five years after creation. \nRequires the Secretary to report to specified congressional committees on: (1) all remaining privately held mineral interests within the boundaries of the Monument; and (2) a plan and a timetable by which the Secretary would propose to complete the acquisition of such interests.\nOutput:" }, { "from": "gpt", "value": "Mount St. Helens National Volcanic Monument Completion Act" } ]

[ { "from": "human", "value": "Q: Given an entity as input, output another entity which is part of the input entity. 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., output entity) is in a part-of relationship with its holonym (i.e., input entity).\ncavity\nA:" }, { "from": "gpt", "value": "muscle wall" } ]

[ { "from": "human", "value": "Teacher:In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element in the reverse order. 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.\nTeacher: Now, understand the problem? Solve this instance: 1, 2, ['7577', 'B', 'M', '6487']\nStudent:" }, { "from": "gpt", "value": "B, 7577" } ]

[ { "from": "human", "value": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to concatenate all elements of A from the ith element to the jth element, and print the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n\n2, 4, ['759', '3797', 'P', '6119', '7147']" }, { "from": "gpt", "value": "3797P6119" } ]

[ { "from": "human", "value": "Q: Evaluate the similarity between them and classify them into classes from 0-5 as follows:\n0 : The two sentences are completely dissimilar.\n1 : The two sentences are not equivalent, but are on the same topic.\n2 : The two sentences are not equivalent, but share some details.\n3 : The two sentences are roughly equivalent, but some important information differs/missing.\n4 : The two sentences are mostly equivalent, but some unimportant details differ.\n5 : The two sentences are completely equivalent, as they mean the same thing.\nSentence 1: Aspen Technology's shares dropped 74 cents, or 23 percent, to close at $2.48 on the Nasdaq. Sentence 2: In afternoon trading, Aspen's shares were off 89 cents or more than 27 percent at $2.33 per share.\nA:" }, { "from": "gpt", "value": "2" } ]

[ { "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 context and a verb separated with a newline character. You have to identify if the given verb implies an opinion, an intention, a wish or not. Please note that a verb refers to an intention only if it refers to an event planned to happen in the future and is not conditional (or part of a condition). The output should be: 'Yes' if the verb refers to an opinion, an intention, or a wish; and 'No' otherwise.\n\nIt was followed by Denmark, Norway, Germany, France, Greece, Luxembourg, Spain, Britain, the United States, Iceland, Belgium, Italy, Portugal and Turkey. NATO decided at last year's Madrid summit to (invite) the three eastern European countries to start accession talks. \n Verb: invite\nSolution: Yes\nWhy? They planned to \"invite\" the three eastern European countries, so this verb refers to an intention.\n\nNew input: The United States had the right to defend its citizens against terrorist actions, New Zealand said Friday in response to U.S. missile attacks on alleged terrorist sites in Sudan and Afghanistan. Foreign Minister Don McKinnon (said) that terrorist bombings this month of U.S. embassies in Nairobi, Kenya and Dar es Salaam, Tanzania, show that terrorism is an indiscriminate killer of innocent people. \n Verb: said\nSolution:" }, { "from": "gpt", "value": "No" } ]

[ { "from": "human", "value": "Detailed Instructions: You are given a math word problem and you are supposed to apply addition or subtraction mathematical operators on the numbers embedded in the text to answer the following question and then only report the final numerical answer.\nProblem:Sam had 9 dimes in his bank . His dad gave him 7 more dimes . How many dimes does Sam have now ?\nSolution:" }, { "from": "gpt", "value": "16" } ]

[ { "from": "human", "value": "Part 1. Definition\nIn 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.\nPart 2. Example\nArticle: 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 Answer: whether mood affects their learning ability\nAnswer: Researchers did experiments on kids in order to find out _ .\nExplanation: It is clearly mentioned in the article that to the check effect of mood on children is the main purpose of the experiment.\nPart 3. Exercise\nArticle: Foreign attacks on U. S. soil 1812 ---- During the War of 1812, British forces burned the new capital at Washington, D. C. They also attacked Baltimore and New Orleans and captured Detroit, which at the time was a remote military outpost . 1846 ---- A brief invasion by Mexican troops across the Rio Gande began the U. S. - Mexican War in 1846. But the remaining action in that conflict occurred in California, New Mexico and in Mexico. California and New Mexico belonged to Mexico at the time. 1916 ---- Mexican revolutionaries led by Pancho Villa attacked the town of Columbus, N. M., on March 9, 1916. 1941 -- Japan attacked Pearl Harbor in Hawaii on Dec. 7, 1941, killing nearly 2,400 people and forcing America into World War II. 1993 ---- Terrorists blew up a truck bomb in the basement of the World Trade Center in February 1993, killing six people and injuring more than 1,000. 2001 ---- Terrorists hijacked several planes on Sep.11, 2001. Two ploughed into New York's World Trade Center (WTC), _ the two highest buildings in the city; a third seriously damaged the Pentagon . The fourth hijacked plane crashed in Pennsylvania. Several thousand people were killed in the attacks. \n Answer: destroyed the Pentagon completely\nAnswer:" }, { "from": "gpt", "value": "During the September 11th terrorist attacks, _ ." } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a four sentences of story written in natural language. Your job is to complete end part of the story by predicting appropriate last sentence which is coherent with the given sentences.\nQ: Sentence1: Coming out of College, I was so nervous to start work. Sentence2: I could barely sleep the week before my start date. Sentence3: The day of, I was nauseous and jittery. Sentence4: However, a congratulatory text from my parents cheered me up.\nA:" }, { "from": "gpt", "value": "I had a great first day of work." } ]

[ { "from": "human", "value": "In this task, you need to count the occurrences of the given word in the given sentence.\nExample: Sentence: 'the brown cat sits perched on atop of the bed peering forward'. Count the occurrences of the word 'the' in the given sentence.\nExample solution: 2\nExample explanation: The word 'the' appears two times in the given sentences. So, the answer is 2.\n\nProblem: Sentence: 'a fudge brownie with chocolate chips sits near a threeprong fork'. Count the occurrences of the word 'a' in the given sentence.\n" }, { "from": "gpt", "value": "Solution: 2" } ]

[ { "from": "human", "value": "In this task, you need to reverse the order of words in the given sentence.\n\nSentence: a very nice table with some laptops on it" }, { "from": "gpt", "value": "it on laptops some with table nice very a" } ]

[ { "from": "human", "value": "Detailed Instructions: Given a premise, an initial context, an original ending, and a counterfactual context, the task is to generate a new story ending aligned with the counterfactual context and as close to the original ending as possible. Each instance consists of a five-sentence story. The premise is the first sentence of a story, and the second sentence, which is the initial context, provides more information about the story's context and the story's general plot. The original ending is the last three sentences of the story. Also, a counterfactual context is a slight modification to the initial context. You should write a new story ending that edits the original story ending as little as possible to regain coherence with the counterfactual context. To sum up, you should write the last three sentences of a story based on the premise(first sentence) and the counterfactual context(second sentence) of the story.\nQ: Premise: It was a windy, rainy day as Tia ran errands downtown. \n Initial Context: A sudden gust ripped her umbrella out of her hand! \n Original Ending: It went sailing off down the street. Luckily, a kind passerby caught the umbrella and returned it to her. Tia thanked the Good Samaritan profusely! \n Counterfactual Context: A sudden gust almost ripped her umbrella out of her hand.\nA:" }, { "from": "gpt", "value": "It went drift behind her and she almost lost it. Luckily, the wind stopped and she regained her grip. Tia was thankful that she didn't have to chase her umbrella. " } ]

[ { "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.\nThe task is to generate text based off of an event. For the given event, there will be a person who does the action in the event (usually PersonX). Your task is to write that persons intent behind doing the event, i.e. why did the person do that action.\n\nPersonX keeps ___ in mind\nSolution: to remember something\nWhy? this is a good example because this is likely why PersonX would keep something in mind.\n\nNew input: PersonX gets home from school\nSolution:" }, { "from": "gpt", "value": "to rest" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you will be presented with a question in Dutch language, and you have to write the part-of-speech tag for each word and punctuation in the question. Here is the list of part-of-speech tags used in this task: Adj: Adjective, Adv: Adverb, Art: Article, Conj: Conjunction, Int: Interjection, N: Noun, V: Verb, Num: Number, Misc: Miscellaneous, Pron: Pronoun, Prep: Preposition, Punc: Punctuation.\nQ: ( FSt )\nA:" }, { "from": "gpt", "value": "Punc N Punc" } ]

[ { "from": "human", "value": "Detailed Instructions: 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.\nProblem:I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_TURN_LEFT\nSolution:" }, { "from": "gpt", "value": "walk around left twice and turn left twice" } ]

[ { "from": "human", "value": "Detailed Instructions: 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: Would you like me to fill out the form ? \n Person2:I suppose so , but don't rush . I've got to tell you how to do it . \n Person1: That's very kind of you . \nA:" }, { "from": "gpt", "value": "informal" } ]

[ { "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\nQuestion: Which of these items has less gravitational strength? \n Answer: the moon" }, { "from": "gpt", "value": "Less massive objects also have less gravity than more massive objects." } ]

[ { "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].\nProblem:[53, 83, -21, 59, -91, 74, 53, 83, 22, -52, 67]\nSolution:" }, { "from": "gpt", "value": "[68.0, 31.0, 19.0, -16.0, -8.5, 63.5, 68.0, 52.5, -15.0, 7.5]" } ]

[ { "from": "human", "value": "In this task, you are given an abstract of article. Your task is to generate title for this article. Preferred titles are under thirty words.\n\n[EX Q]: CONTEXT The long-term risk for developing hypertension is best described by the lifetime risk statistic. The lifetime risk for hypertension and trends in this risk over time are unknown. \n OBJECTIVES To estimate the residual lifetime risk for hypertension in older US adults and to evaluate temporal trends in this risk. \n DESIGN, SETTING, AND PARTICIPANTS Community-based prospective cohort study of 1298 participants from the Framingham Heart Study who were aged 55 to 65 years and free of hypertension at baseline (1976-1998). \n MAIN OUTCOME MEASURES Residual lifetime risk (lifetime cumulative incidence not adjusted for competing causes of mortality) for hypertension, defined as blood pressure of 140/90 mm Hg or greater or use of antihypertensive medications. \n RESULTS The residual lifetime risks for developing hypertension and stage 1 high blood pressure or higher (greater-than-or-equal to 140/90 mm Hg regardless of treatment) were 90% in both 55- and 65-year-old participants. The lifetime probability of receiving antihypertensive medication was 60%. The risk for hypertension remained unchanged for women, but it was approximately 60% higher for men in the contemporary 1976-1998 period compared with an earlier 1952-1975 period. In contrast, the residual lifetime risk for stage 2 high blood pressure or higher (greater-than-or-equal to 160/100 mm Hg regardless of treatment) was considerably lower in both sexes in the recent period (35%-57% in 1952-1975 vs 35%-44% in 1976-1998), likely due to a marked increase in treatment of individuals with substantially elevated blood pressure. \n CONCLUSION The residual lifetime risk for hypertension for middle-aged and elderly individuals is 90%, indicating a huge public health burden. Although the decline in lifetime risk for stage 2 high blood pressure or higher represents a major achievement, efforts should be directed at the primary prevention of hypertension.\n[EX A]: Residual lifetime risk for developing hypertension in middle-aged women and men: The Framingham Heart Study.\n\n[EX Q]: Evidence suggests that dormant, microscopic tumors are not only common, but are highly prevalent in otherwise healthy individuals. Due to their small size and non-invasive nature, these dormant tumors remain asymptomatic and, in most cases, undetected. With advances in diagnostic imaging and molecular biology, it is now becoming clear that such neoplasms can remain in an asymptomatic, dormant stage for considerable periods of time without expanding in size. Although a number of processes may play a role in thwarting the expansion of microscopic tumors, one critical mechanism behind tumor dormancy is the ability of the tumor population to induce angiogenesis. Although cancer can arise through multiple pathways, it is assumed that essentially most tumors begin as microscopic, non-angiogenic neoplasms which cannot expand in size until vasculature is established. It is now becoming clear that cancer does not progress through a continuous exponential growth and mass expansion. Clinical cancer is usually manifested only in late, unavoidably symptomatic stages of the disease when tumors are sufficiently large to be readily detected. While dormancy in primary tumors is best defined as the time between the carcinogenic transformation event and the onset of inexorable progressive growth, it can also occur as minimal residual or occult disease from treated tumors or as micro-metastases. The existence of dormant tumors has important implications for the early detection and treatment of cancer. Elucidating the regulatory machinery of these processes will be instrumental in identifying novel early cancer biomarkers and could provide a rationale for the development of dormancy-promoting tumor therapies. Despite the high prevalence of microscopic, dormant tumors in humans and the significant clinical implications of their early detection, this area in cancer research has, to date, been under-investigated. In this mini review observations, models and experimental approaches to study tumor dormancy are summarized. Additionally, analogies and distinctions between the concepts of \"tumor dormancy\" and that of the \"cellular dormancy\" of tumor cells, as well as between the \"exit from tumor dormancy\" and the \"onset of the angiogenic switch\" are discussed.\n[EX A]: Molecular mechanisms underlying tumor dormancy.\n\n[EX Q]: Precursor cells of the embryonic cortex sequentially generate neurons and then glial cells, but the mechanisms regulating this neurogenic-to-gliogenic transition are unclear. Using cortical precursor cultures, which temporally mimic this in vivo differentiation pattern, we demonstrate that cortical neurons synthesize and secrete the neurotrophic cytokine cardiotrophin-1, which activates the gp130-JAK-STAT pathway and is essential for the timed genesis of astrocytes in vitro. Our data indicate that a similar phenomenon also occurs in vivo. In utero electroporation of neurotrophic cytokines in the environment of embryonic cortical precursors causes premature gliogenesis, while acute perturbation of gp130 in cortical precursors delays the normal timed appearance of astrocytes. Moreover, the neonatal cardiotrophin-1-/- cortex contains fewer astrocytes. Together, these results describe a neural feedback mechanism; newly born neurons produce cardiotrophin-1, which instructs multipotent cortical precursors to generate astrocytes, thereby ensuring that gliogenesis does not occur until neurogenesis is largely complete.\n[EX A]:" }, { "from": "gpt", "value": "Evidence that Embryonic Neurons Regulate the Onset of Cortical Gliogenesis via Cardiotrophin-1\n\n" } ]

[ { "from": "human", "value": "instruction:\nIn this task you are expected to fix an SQL query based on feedback. You will be given an SQL statement and an English description with what is wrong about that SQL statement. You must correct the SQL statement based off of the feedback. An SQL query works by selecting data from a table where certain conditions apply. A table contains columns where every row in that table must have a value for each column. Every table has a primary key that uniquely identifies each row, usually an id. To choose which columns are returned you specify that after the \"SELECT\" statement. Next, you use a \"FROM\" statement to specify what tables you want to select the data from. When you specify a table you can rename it with the \"AS\" statement. You can reference that table by whatever name follows the \"AS\" statement. If you want to select data from multiple tables you need to use the \"JOIN\" statement. This will join the tables together by pairing a row in one table with every row in the other table (Cartesian Product). To limit the number of rows returned you should use the \"ON\" statement. This will only return rows where the condition specified after the statement is true, this is usually an equals operator with primary keys. You can also use the \"WHERE\" statement to specify that only rows with column values statisfying a certain condition, should be returned. The \"GROUP BY\" statement will group rows together that have equal column values for whatever columns follows the statement. The \"HAVING\" statement will return groups that statisfy whatever condition follows the statement. Any column(s) being returned from grouped rows must either be an aggregate function, (AVG, MAX, COUNT, SUM, ...) of a column, or the column(s) that the data was grouped by. To sort the returned data you can use the \"ORDER BY\" command which will order the data by whatever aggregate function or column follows the statement. The \"DESC\" statement will sort in descending order and the \"ASC\" statement will sort in ascending order. Finally, you can use the \"LIMIT\" statement to return a certain number of rows. When \"*\" is used in an SQL statement every column is returned. For example, SELECT * FROM table WHERE attribute = 1, will select every column from rows with the attribute column equal to 1. \nquestion:\nSQL: SELECT Avg ( other_customer_details ) FROM Customers\nFeedback: Find the average order quantity in order items table for each value of order id .\nanswer:\nSELECT avg(order_quantity) FROM order_items\n\n\nquestion:\nSQL: SELECT FirstName , LastName FROM list WHERE FirstName = \"OTHA\"\nFeedback: Ensure last name is MOYER and first name and last name both are in corresponding teachers table .\nanswer:\nSELECT T1.firstname , T1.lastname FROM list AS T1 JOIN teachers AS T2 ON T1.classroom = T2.classroom WHERE T2.firstname = \"OTHA\" AND T2.lastname = \"MOYER\"\n\n\nquestion:\nSQL: SELECT Max ( T2.length_feet ) FROM architect AS T1 JOIN bridge AS T2 ON T1.id = T2.architect_id WHERE T1.name = \"Frank Lloyd Wright\"\nFeedback: Replace length feet with length meters , find architect's names for bridge , remove whole last part of step 2.\nanswer:\n" }, { "from": "gpt", "value": "SELECT max(T1.length_meters) , T2.name FROM bridge AS T1 JOIN architect AS T2 ON T1.architect_id = T2.id\n\n\n" } ]

[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you're given the title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story; note that the selected choices may fit into the story at any point. Indicate your selected choices in order, i.e., as 'ab'/'bc'/'ac' and not as 'ba'/'ca'/'cb'. If options are equally plausible, pick the ones that make more sense.\nExample: Title: Marcus Buys Khakis. Marcus needed clothing for a business casual event. He decided to buy a pair of khakis. The pair he bought fit him perfectly. Choices: a. Marcus was happy to have the right clothes for the event. b. He left in a huff for having his ideas mocked. c. All of his clothes were either too formal or too casual.\nOutput: ac\nMarcus is buying clothes for a business event and not presenting an idea.\n\nNew input case for you: Title: My Dad was in the military when I was in elementary and middle school. We did not settle into a community until I was in high school. At school, I did not have adjustment problems unlike most of my peers. Choices: a. I had to learn how to quickly adapt to new people and new cultures. b. His friends realized too late that the cord wasn't attached right. c. We had to move around a lot to different parts of the country.\nOutput:" }, { "from": "gpt", "value": "ac" } ]

[ { "from": "human", "value": "Generate a question which can yield the answer mentioned in the input. Generated question must be answered by the answer provided in input, without using any extra knowledge.\nExample: Context : Isaac Nicola Romero (1916 in Havana, Cuba -- 1997) was a prominent Cuban guitarist and one of the founders of the modern Cuban Guitar School. \nAnswer : Havana\nExample solution: What was Isaac Nicola's city of birth?\nExample explanation: The answer to the generated question according to context is Havana which is correct\n\nProblem: Context : Napoleon Dynamite was acquired at the Sundance Film Festival by Fox Searchlight Pictures and Paramount Pictures, in association with MTV Films. \nAnswer : Fox Searchlight Pictures\n" }, { "from": "gpt", "value": "Solution: What studio produced Napoleon Dynamite?" } ]

[ { "from": "human", "value": "Detailed Instructions: 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'.\nProblem: Person1: This is where we sing ? These booths are so comfortable , I think I could fall asleep ! \n Person2:Let's order something to eat . What are you in the mood for ? \n Person1: I'll have whatever you're having . \n Person2:OK . How about some fried spring rolls and squid balls , some pork skins , and some beer ! \n Person1: Well ... the beer sounds good ! \nSolution:" }, { "from": "gpt", "value": "informal" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a statement spoken by a politician in natural language. Your task is to generate the subject of the discussion for the given statement. The subject generated is not necessarily a part of the given input. Your answer should contain one or more words.\nSee one example below:\nProblem: Says the Annies List political group supports third-trimester abortions on demand.\nSolution: abortion\nExplanation: It's a correct subject of the statement because it talks about a political group supporting demans of abortions.\n\nProblem: Says Alex Sink failed Florida homeowners by using predatory lending practices.\nSolution:" }, { "from": "gpt", "value": "corporations" } ]

[ { "from": "human", "value": "You are given a math word problem and you are supposed to apply division mathematical operator on the numbers embedded in the text to answer the following question and then only report the final numerical answer.\n\nContext: He then went to see the oranges being harvested. He found out that they harvest 16 sacks per day and that each sack containes 57 oranges. \n\n Question: How many days will it take to harvest 80 sacks of oranges?" }, { "from": "gpt", "value": "5" } ]

[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, we ask you convert a data table of restaurant descriptions into fluent natural-sounding English sentences. The input is a string of key-value pairs; the output should be a natural and grammatical English sentence containing all the information from the input.\n\nname[Aromi], eatType[coffee shop], food[French], customer rating[low], area[riverside], familyFriendly[no]\n" }, { "from": "gpt", "value": "Aromi is a coffee shop. It is located close to the city center. and has a superb view across the river. It doesn't provide family-style dining." } ]

[ { "from": "human", "value": "Instructions: In this task you are given a sentence with one coordinating conjunction (for, and, nor, but, or, yet, and so). You must judge whether the order of two coordinated clausal conjoints have been inverted or not. Inversion would result in the sentence sounding unnatural. Label the instances as \"Original\" or \"Inversion\" based on your judgment.\nInput: I didn 't have a choice , but normally I wasn 't a gambling person .\nOutput:" }, { "from": "gpt", "value": "Inversion" } ]

[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nYou are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to choose the correct answer to the question based on the passage. Answer of the question cannot be found directly from the passage, it is indirectly indicated in the passage. Do not answer with words other than the two options, and do not answer with option titles(e.g. \"option1\" or \"1\" are not acceptable answers.)\nExample: Passage: Omelettes make a great breakfast , and I enjoy making them because they are very easy to cook . First , I get the eggs out and begin cracking them on the side of the bowl and dumping them into the bowl . I normally use two eggs whites and one whole egg to cut the calories . I add some salt and pepper to the mix for flavor . I pour the mixture into the hot frying pan . I make sure that I add some vegetable oil to the pan before I add the eggs though because I do n't want them to stick . As this occurs , I add some cheese or vegetable to the center of the egg mixture . Really , almost any type of cheese or vegetable makes a good omelette . I then flip one side of the omelette over on to itself to seal in the contents in the middle . It is then ready to serve ! Question: Where is the omelette being browned? Option1: In the pan Option2: On the street\nOutput: In the pan\nAs mentioned in the passage that I pour the mixture into the hot frying pan; it is clear that omelette is being browned in pan only. Also, there is nothing related to street mention in the passage.\n\nNew input case for you: Passage: I had a craving for eggs the other morning , so I decided to make an omelette . First , I got out 2 eggs and cracked them into a bowl . I sprinkled a little salt and pepper into the eggs . Next , I sprayed a small frying pan with cooking spray and started it heating on the stove while I beat the eggs with a whisk . I lifted the pan slightly and swirled the eggs around until they covered the bottom , then I set the pan down and let the eggs cook slowly . While they cooked , I got out some cheese , ham , chopped onion , and chopped green peppers . When the eggs looked fairly well set on top , I placed the cheese , ham , and vegetables on top . I put a lid on the pan and let it heat a little longer until the cheese was melted . Then I ate my omelette ! Question: When did the person pour the eggs into the pan? Option1: after cooking Option2: After beating them\nOutput:" }, { "from": "gpt", "value": "After beating them" } ]

[ { "from": "human", "value": "instruction:\nIn this task, you're given a short story of five sentences written in natural language. However, the order of the given story is not correct. Your job is to return the correct order for the given five sentences to create a coherent short story with the new order that has the correct flow. Generate your answer using the number of sentences in the correct order, such as '23415'.\nquestion:\nSentence1: Azalea was very cool. Sentence2: The concert was amazing. Sentence3: After the show I went backstage to meet her. Sentence4: I got to be in the front row. Sentence5: Last Saturday I went to an Azalea concert.\nanswer:\n52431\n\n\nquestion:\nSentence1: In 2005, I went to St Anselm College to play chess. Sentence2: I was on a great streak and did not lose any games! Sentence3: I will continue playing chess and hope for qualified opponents. Sentence4: My friend was a professor there. Sentence5: His colleague-also a chess player- played us as well.\nanswer:\n14523\n\n\nquestion:\nSentence1: I went to the interview and was happy to get the job. Sentence2: I applied to many different places. Sentence3: One place called me back and I went for an interview. Sentence4: Recently, I became very unhappy with my job. Sentence5: I decided to look around for a new one so I would be happy.\nanswer:\n" }, { "from": "gpt", "value": "53412\n\n\n" } ]

[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you are given product reviews about dvds. The goal is to classify the review as \"POS\" if the overall sentiment of the review is positive(the reviewer is satisfied) or as \"NEG\" if the overall sentiment of the review is negative(the reviewer is not satisfied).\n\nEight Men Out . The film is fantastic for all baseball lovers, history lovers, and anyone who wishes to escape for a few hours. No baseball fan should miss this one\n" }, { "from": "gpt", "value": "POS" } ]

[ { "from": "human", "value": "In this task, you are given a sentence containing a particular emotion. You must classify the sentence into one of the six emotions: 'joy', 'love', 'anger', 'fear', or 'surprise'.\n\nInput: Consider Input: i feel like supporting local and indie businesses is extra important for me since i run one myself\n\nOutput: love\n\n\nInput: Consider Input: i ended the episode feeling really pissed\n\nOutput: anger\n\n\nInput: Consider Input: i want to stop feeling so worthless\n\n" }, { "from": "gpt", "value": "Output: sadness\n\n\n" } ]

[ { "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\nExample input: Je kunt een mandje gebruiken om de prullenbak te vervangen.\nExample output: Je kunt een mand gebruiken om afval weg te gooien.\nExample explanation: This is a good change in the input, because it is semantically similar to the input as both are talking about using a basket to through trash/garbage and the output sentence follows the commonsense knowledge.\nQ: Op je trouwdag zou je zeggen dat je van je vrouw houdt.\nA:" }, { "from": "gpt", "value": "Op je mobiel zou je zeggen dat je je vrouw belt." } ]

[ { "from": "human", "value": "Generate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words.\n\nEx Input:\nSentence1: Methane gas is a produced by rotting compost, trash, and human waste. \nSentence2: Methane gas can be produced by Slime molds.\n\nEx Output:\nMethane\n\n\nEx Input:\nSentence1: Basically the process is pretty simple. \nSentence2: All cells share some of the same structures and simple processes.\n\nEx Output:\nprocess\n\n\nEx Input:\nSentence1: Bioterrorism is another potential threat in the environment. \nSentence2: bioterrorism is silent.\n\nEx Output:\n" }, { "from": "gpt", "value": "Bioterrorism\n\n\n" } ]

[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nThis task is about translating a given English language sentence to French.\n\nLooking for a man who will fuck me in front of my impotent husband\nOutput:" }, { "from": "gpt", "value": "Je cherche un homme qui me baise devant mon mari impuissant" } ]

[ { "from": "human", "value": "Q: You are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to find the correct answer (and return the string of the correct option, not option1/2) for the given question from the given options and based on the given passage. Answer of the question can be found directly from the passage.\nPassage: Today I went to a football match with my friend Alex. Alex and I met at his house and drove together from there . We paid $ 5 each for our tickets at the gate , and stopped to buy popcorn before making our way to our seats . We sat in the seventh row , close to the field . The players ran out onto the field and we cheered loudly for our team . The ball started with the opposing team but our star player kicked it away and made a goal . We stood up and cheered . The teams were well paired and many goals were blocked by the keepers for each team . We hardly stayed in our seats . In the end our team one and we were very happy . Question: What was the outcome of the match? Option1: The narrator's preferred team won Option2: the other team won\nA:" }, { "from": "gpt", "value": "The narrator's preferred team won" } ]

[ { "from": "human", "value": "Q: You are given an open-domain question from an open movie database. Your task is to provide an answer to that question. Try to only include the answer. Do not put it in a sentence.\nwho acted in the movie Kickboxer?\nA:" }, { "from": "gpt", "value": "Jean-Claude Van Damme, Dennis Chan, Michel Qissi, Dennis Alexio" } ]

[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nYou are asked to create a question containing a blank (_), based on the given context word. Your question must contain two related but different objects; for example \"trophy\" and \"suitcase\". The expected answer to your question must be one of the objects present in the sentence. The expected answer must not be associated with any specific word in the question; instead it should depend on the context present in the question. The expected answer should not be equally likely to fill the blank. For your question, there should be a agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals or proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style, pattern or phrases in each question, try to increase diversity by varying sentence structure, blank placement etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Object X and Y have the same number e.g. when ObjectX is singular, Object Y must be singular, too. The two objects (Object X & Object Y) should be used ONCE in your question. Here is a list of attributes and associated pair of contrastive words which may be used to create a valid question using the objects. You can use either of the contrastive words, but not both. You should think about more such attributes and associated words and use them in your question.\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: hotel.\nOutput:" }, { "from": "gpt", "value": "Jimmy wanted to learn how to learn about the hotel market so he took a class but the _ is empty." } ]

[ { "from": "human", "value": "Teacher:Given a story, answer the question about the story. The question is the last sentence in the input. The story has one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios. Note that there are distractor sentences in each story that are unrelated to the question and are designed to confuse the reader.\nTeacher: Now, understand the problem? Solve this instance: Alexander entered the office. Mia entered the office. The onion is in the blue_suitcase. Mia exited the office. Alexander moved the onion to the green_envelope. Phone rang. Alexander exited the office. Mia entered the office. Where was the onion at the beginning?\nStudent:" }, { "from": "gpt", "value": "blue_suitcase" } ]

[ { "from": "human", "value": "Given a comment text in Tamil, classify the comment into one of these categories (i) Hope speech, if it contains encouraging, positive or supportive contents about equality, diversity or inclusion, (ii) Not Hope Speech or (iii) Not in Expected Language, if the text is not Tamil.\n\nRealme X3 video eppa varum\nHope Speech\n\nEven me sis\nNot Hope Speech\n\n@Cloud Tech ska\n" }, { "from": "gpt", "value": "Not in Expected Language\n\n" } ]

[ { "from": "human", "value": "In this task, you are given an utterance, which is a part of a conversation between a user and an agent. Your job is to detect the speaker. The user usually commands the agent to schedule events, retrieve event information, and check the schedule. While the agent's response is an answer to the user's questions or follow-up questions on the user's command. Answer with \"User\" or \"Agent\".\n\n[EX Q]: Yup\n[EX A]: user\n\n[EX Q]: Read for me what is on my calender this afternoon\n[EX A]: user\n\n[EX Q]: No, it is with Alice and not Tim.\n[EX A]:" }, { "from": "gpt", "value": "user\n\n" } ]

[ { "from": "human", "value": "instruction:\nIn 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.\nquestion:\nQuestion: A person is digging up rocks, and wants to get the oldest ones. The person will dig \n Answer: deeper\nanswer:\nOlder rocks are at the bottom and younger rocks are at the top.\n\n\nquestion:\nQuestion: Dave is taking water samples from various parts of Lake Erie. He takes the first sample very far from the shore line. The second sample he takes from the edge of the lake. He expects that the _____ sample will have more nutrients in it/ \n Answer: second\nanswer:\nMost nutrients are washed into ocean water from land. Therefore, water closer to shore tends to have more nutrients.\n\n\nquestion:\nQuestion: While checking the weather, Dale noticed that there was an inverse relationship between the temperature and atmospheric pressure. So as it was getting warmer, he should expect the atmospheric pressure to \n Answer: decrease\nanswer:\n" }, { "from": "gpt", "value": "Decreasing air temperature increases atmospheric pressure.\n\n\n" } ]

[ { "from": "human", "value": "In this task, you will be shown a conversation and a question. You need to answer the question and choose the correct option based on the conversation. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\n\nExample Input: M: What do you often do in your free time? W: I enjoy flying kites in spring, swimming in summer and skating in winter. What about you? M: I enjoy playing basketball when I'm free., Question: What does the girl enjoy doing in her free time in spring? (A) Flying kites. (B) Swimming. (C) Skating.\nExample Output: (A) Flying kites.\n\nExample Input: M: This is Officer Belford. You reported a break-in just now? W: Yes, I did. M: I'll need a little more information about it. W: Just the facts. M: What time did it happen? W: It must have been sometime between 12:00 and 1:30 because I was home until almost 12:00 and I just got back at 1:30. M: What did they get? W: Well, what I know now is some jewellery and the television. M: OK. Good, you're making a list. By the way, did you have your belongings marked? W: Yes. My husband put his name on the TV. M: By the way, where is your husband? W: He's on a trip to Canada. And I haven't told him about the robbery. M: I see, where did you put your jewellery? W: I put it in the refrigerator. But all my good jewellery is in the safe box in the bank. M: OK. I'll be in touch with you as soon as we have found anything about it., Question: When was the woman's house broken into? (A) At about 12:00. (B) At about 1:30. (C) Between 12:00 and 1:30.\nExample Output: (C) Between 12:00 and 1:30.\n\nExample Input: M: Shall we go to the park tomorrow? W: Good idea. What should I take? M: Your camera, please., Question: What does the man tell the woman to take? (A) Her umbrella. (B) Her camera. (C) Her hat.\nExample Output:" }, { "from": "gpt", "value": "(B) Her camera.\n\n" } ]

[ { "from": "human", "value": "Detailed Instructions: Given a set of five words, generate the word from the set that does not belong (i.e. is the least relevant) with the other words. Words are separated by commas.\nSee one example below:\nProblem: excavator, crane, pelican, hoist, upraise\nSolution: pelican\nExplanation: The common category here are words related to construction. A pelican is not related to construction because it is a type of bird.\n\nProblem: suits, deck, board, fold, stern\nSolution:" }, { "from": "gpt", "value": "stern" } ]

[ { "from": "human", "value": "Q: In this task, you are given a text from tweets and a boolean question whether this tweet has positive sentiment or negative sentiment. Your task is to generate answer \"yes\" when the tweet has that particular sentiment, otherwise generate answer \"no\".\nTweet: Finally found the relevant bits of paper! I think I need a PA! Question: is it a positive tweet?\nA:" }, { "from": "gpt", "value": "yes" } ]

[ { "from": "human", "value": "Part 1. Definition\nIn this task, you are given a sentence and a profession that is mentioned in the sentence. The gender of the person with the given profession can be identified using the gendered pronouns that refer to them in the text. You are expected to identify the gender. Select from female and male.\nPart 2. Example\nSentence: The mover helped the writer to pack up otherwise he needed to wait for another two hours.\n Profession: mover\nAnswer: Male\nExplanation: The pronoun \"he\" is linked to the mover and thus the mover is a male.\nPart 3. Exercise\nSentence: The mover refused to move the artwork where the designer asked and demanded she reconsider.\n Profession: designer\nAnswer:" }, { "from": "gpt", "value": "Female" } ]

[ { "from": "human", "value": "In this task, you will be given sentences in which you have to recognize the name of the body cells. A cell is a mass of cytoplasm that is bound externally by a cell membrane. Usually microscopic in size, cells are the smallest structural units of living matter and compose all living things. Although there might be several correct answers, you need to write one of them.\n--------\nQuestion: Young mice can increase the cellular availability of GSH , whereas mature mice can increase GSH synthetase activity during oxidative stress .\n\nAnswer: cellular\n\n\nQuestion: Defective expression of the granulocyte - macrophage colony - stimulating factor receptor was ruled out .\n\nAnswer: macrophage\n\n\nQuestion: Particularly Egr1 ( Fig . 6B ) and Egr2 ( Fig . 6C ) mRNA levels were almost identical when comparing neurons treated with BDNF alone and neurons with BDNF and ephrin - A5 together .\n\nAnswer:" }, { "from": "gpt", "value": "neurons\n\n\n" } ]

[ { "from": "human", "value": "In this task, you are given inputs 'i', 'j', and A, where 'i' and 'j' are integers and A is a list. A list is shown by two brackets and comma-separated numbers and characters inside, like ['1', '12', 'l']. You need to concatenate all elements of A from the ith element to the jth element, and then reverse the resulting string. 'i' and 'j' will be non-negative, and will always have a value less than the length of A. 'i' will always be less than 'j'. Perform the operations in order, i.e., do not reverse first and then concatenate.\n\n[EX Q]: 5, 6, ['u', 'O', 'l', '9119', 'P', '6983', 'H', '6701']\n[EX A]: 3896P\n\n[EX Q]: 12, 29, ['4267', '7621', 'e', 'd', '2685', '3417', 'V', 'E', '3849', '6875', '1093', '9451', '3257', '6313', 'K', 'j', '3551', 'l', 'J', 't', 'V', '7965', '307', 'A', '3733', 'Y', '8649', '8475', 'X']\n[EX A]: X57489468Y3373A7035697VtJl1553jK313675231549\n\n[EX Q]: 10, 27, ['407', 'b', 's', '3171', '8461', '4681', '5237', 't', '5871', '447', 'S', 'c', 'd', '1421', '3011', '821', '8683', '3203', '2079', 'N', 'F', 'E', 'H', '8773', '2259', 'K', 'f']\n[EX A]:" }, { "from": "gpt", "value": "fK95223778HEFN97023023386812811031241dcS744\n\n" } ]

[ { "from": "human", "value": "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.\nOne example is below.\nQ: Personality: I like spending time with my friends and family.\nI like listening to all genres of music except country music.\nI like to read a lot of books.\nChat history: -Hi.\n -Hey how are you?\n -Good and yourself?\n -Good, just listening to music and hanging out with my family.\n -What do you do for a living?\n -I am a teacher. How about you?\n -I'm a vet at the animal shelter.\n -That is awesome, what do you like to do for fun?\n -I love running. Its my way to detox.\n -Running is great. Do you have any other hobbies?\n -Not really... what do you teach?\n -I teach reading, I love books and helping children learn how to read.\n -Where are you from?\nCandidates 1) Care to chat with a hamburger lover? Its my fav food. 2) I bet that is a great place to draw. I sell art for a living. 3) I am from Illinois, how about you? 4) They're great pets! I just started an organic only diet.\nA: I am from Illinois, how about you?\nRationale: The third choice is the best answer to the last part of the conversation, that asks where the person is from.\nQ: 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.\nA:" }, { "from": "gpt", "value": "I'm good! Does your cat like sweet stuff?" } ]

[ { "from": "human", "value": "Detailed Instructions: Given a sentence, generate a new 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.\nProblem:A friend 's proposal would make you prefer to go to a boat .\nSolution:" }, { "from": "gpt", "value": "A friend 's success would make you want to go to a ski ." } ]

[ { "from": "human", "value": "Part 1. Definition\nIn 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.\nPart 2. Example\nWho were the builders of the mosque in Herat with fire temples ?\nAnswer: Ghurids\nExplanation: This is a good example. Ghurids were the builders of the mosque in Herat with fire temples.\nPart 3. Exercise\nWhen did this incident happen for which this politician representing this district known for its two major cities of Greenville and Spartanburg represented ?\nAnswer:" }, { "from": "gpt", "value": "May 22 , 1856" } ]

[ { "from": "human", "value": "Detailed Instructions: Generate an appropriate title for the given text. The generated title must be short and include the main topic of the text. The preferred titles are under fifteen words.\nQ: PNG Prime Minister Peter O'Neill said in a statement he had met Australia's immigration minister, Peter Dutton, in Port Moresby on Wednesday. \"Both PNG and Australia are in agreement that [Manus Island] centre is to be closed,\" the statement said. PNG's Supreme Court found in April that detaining asylum seekers and refugees at the centre was unconstitutional. Mr O'Neill said the Manus Regional Processing Centre, which currently houses 854 men, would not close immediately. What next for Manus Island asylum seekers? \"A series of options are being advanced and implemented,\" Mr O'Neill said. \"It is important that this process is not rushed but carried out in a careful manner. \"This must take into account the interests of the people of Papua New Guinea and the wellbeing of asylum seekers and refugees.\" 'No settlement in Australia' Australia sends asylum seekers who arrive in the country by boat to offshore detention centres in Manus Island and the Pacific nation of Nauru. Even those who are found to be genuine refugees are not allowed to settle in Australia. Mr Dutton said in a statement that the Australian government \"had a longstanding position\" to work with PNG's government to close Manus Island and resettle refugees. \"Our position, confirmed again today with PNG, is that no one from Manus Island Regional Processing Centre will ever be settled in Australia,\" the statement said. Manus Island: A controversial 'solution' Manus Island: Australia's Guantanamo? Australia's controversial asylum policy Five judges on Papua New Guinea's Supreme Court's bench ruled in April that the Manus Island camp breached section 42 of the constitution, which guarantees personal liberty. The court said \"all steps\" should be taken to end the \"illegal\" detention. 'Rights and dignity' Papua New Guinea's constitution guarantees personal liberty for all people, except in defined circumstances relating to crime, illegal immigration and quarantine. In 2014, Papua New Guinea's government amended section 42 of the constitution to add a paragraph that allowed for \"holding a foreign national under arrangements made by Papua New Guinea with another country\". But the Supreme Court ruled this amendment was unconstitutional, as it did not meet a requirement to respect \"the rights and dignity of mankind\". Mr Dutton said after the decision in April that there was excess capacity at Nauru to house the detainees from Manus Island. Australia could also reopen its centre on Christmas Island to house the men. The leak of 2,000 incident reports from the detention centre on Nauru detailing sexual assault, violence and self harm have thrust Australia's treatment of asylum seekers back into the spotlight in recent weeks.\nA:" }, { "from": "gpt", "value": "Australia to close Manus Island asylum centre" } ]

[ { "from": "human", "value": "You are given an original reference as well as a system reference. Your task is to judge the quality of the system reference. If the utterance is grammatically correct and fluent output 1, else output 0.\n\nSystem Reference: so you are looking for something in the pricey price range, is that correct?\nOriginal Reference: are you looking for a pricey hotel?.\n0\n\nSystem Reference: what area are you looking for?\nOriginal Reference: in what area were you wanting to dine?.\n0\n\nSystem Reference: what part of the city are you looking for?\nOriginal Reference: what area would you like?.\n" }, { "from": "gpt", "value": "1\n\n" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you will be shown a conversation and a question. You need to answer the question and choose the correct option based on the conversation. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\nProblem:M: Shall we go to the park tomorrow? W: Good idea. What should I take? M: Your camera, please., Question: What does the man tell the woman to take? (A) Her umbrella. (B) Her camera. (C) Her hat.\nSolution:" }, { "from": "gpt", "value": "(B) Her camera." } ]

[ { "from": "human", "value": "In this task, you are given a review of a movie and a boolean question whether this review has positive sentiment or negative sentiment. Your task is to generate answer \"yes\" when the tweet has that particular sentiment, otherwise generate answer \"no\".\nOne example: Review: For a movie that gets no respect there sure are a lot of memorable quotes listed for this gem. Imagine a movie where Joe Piscopo is actually funny! Maureen Stapleton is a scene stealer. The Moroni character is an absolute scream. Watch for Alan The Skipper Hale jr. as a police Sgt. Question: is it a positive review?\nSolution is here: yes\nExplanation: There is an expression of appreciation in this movie review, hence we can say it's positive. So generated label is 'yes'.\n\nNow, solve this: Review: Now i have read some negative reviews for this show on this website and quite frankly I'm appalled. For anyone to even think that the Sopranos is not Television then i'm afraid i don't know what the world has come to. Let me tell u something. I started watching many T.V shows like Lost, Prison Break, Dexter, Deadwood and even Invasion. But all of those shows lost their touch after the first season, especially Lost and Prison Break which i refuse to watch because the companies took 2 genius ideas and butchered them by making more than one season. Then we have The Sopranos. I can honestly say that this is the only television series that i have ever watched where i have been enthralled in all of its season, and more importantly all of its episodes. There is no department that this show doesn't excel in. Acting- Nothing short of superb. James Gandolfini is one of my favourite actors and i feel that his acting is absolutely stunning in every episode, after i heard that HBO wanted Ray Liotta to play Tony i felt that it would've been the better choice, however after watching the first few episodes, i knew that HBO had done a great job in casting James as Tony. The raw emotion he displays is superb. Then we have everyone else, Edie Falco, Michael Imperioli, Lorraine Bracco, Dominic Chianese (whom i remembered as Johnny Ola in the Godfather Part 2) and my personal two favourite characters Tony Sirico and Steve Van Zandt Paulie 'Walnuts' Gualtieri and Silvio Dante. All of these actors perform to the best quality, and all giving an excellent performance in each episode. Then we have the story, never have i been so sucked into a T.V show before. The story is nothing short of excellent. Each episode is directed superbly and the Score of this show is just fantastic. I feel that The Sopranos is one show that i can watch again and again and never get bored of. Its got everything from hilarious humour to brutal violence, but nonetheless it is and will always be the best thing to ever grace the Television, and I challenge anyone to find a real flaw in the show. Not just say its too violent, or they feel that the character of Tony is immoral, i mean it is a mafia show at the end of the day, i don't think that the characters are going to be very honest or loyal to God. I implore everyone to watch this show because believe me, you'll be hooked from the very first episode, i was and i have even gotten a few friends who had firstly refused to watch the show, hooked on it. Trust me when i say that this show is a Godsend compared to the crap that comes on T.V. After you've watched the first season, you'll inevitably agree with me when i once again say that this show dominates Television, and no T.V show current or future will ever upstage the marvel that is The Sopranos. Question: is it a negative review?\nSolution:" }, { "from": "gpt", "value": "no" } ]

[ { "from": "human", "value": "Q: 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 fine labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e tagset of this corpus is : '$': Dollar Sign, \"''\": Single Quotes, ',': Comma Symbol, '-LRB-': Left Parantheses, '-RRB-': Right Parantheses, '.': Period, ':': Colon, 'ADD': Email Address, 'AFX': Affix, 'CC': Coordinating conjunction, 'CD': Cardinal Number, 'DT': Determiner, 'EX': Existential there, 'FW': Foreign Word, 'GW': Go with, 'HYPH': Hyphen symbol, 'IN': Preposition or a subordinating conjunction, 'JJ': Adjective, 'JJR': A comparative Adjective, 'JJS': A Superlative Adjective, 'LS': List item Marker, 'MD': Modal, 'NFP': Superfluous punctuation, 'NN': Singular Noun, 'NNP': Singular Proper Noun, 'NNPS': Prural Proper Noun, 'NNS': Prural Noun, 'PDT': Pre-determiner, 'POS': Possessive Ending, 'PRP': Personal pronoun, 'PRP$': Possessive Pronoun, 'RB': Adverb, 'RBR': Comparative Adverb, 'RBS': Superlative Adverb, 'RP': Particle, 'SYM': Symbol, 'TO': To , 'UH': Interjection, 'VB': Base form Verb, 'VBD': Verb in Past tense, 'VBG': Verb in present participle, 'VBN': Verb in past participle, 'VBP': Verb in non-3rd person singular present, 'VBZ': Verb in 3rd person singular present, 'WDT': Wh-determiner, 'WP': Wh-pronoun, 'WP$' Possessive Wh-pronoun, 'WRB': Wh-adverb, 'XX': Unknown, '``': Double backticks.\nSentence: Israel 's security interests are best served by peace with its neighbors , which can only be achieved by trading land for peace with the {{ Palestinians }} . \nWord: Palestinians\nA:" }, { "from": "gpt", "value": "NNPS" } ]

[ { "from": "human", "value": "In this task you are given a sentence. You must judge whether there exist two consecutive words within the sentence with flipped orders, that is, whether the sentence will make sense and be correct if the order of two consecutive words changes. Label the instances as \"Inversion\" or \"Original\" based on your judgment.\nQ: This is my Eve Christmas.\nA: " }, { "from": "gpt", "value": "Inversion" } ]

[ { "from": "human", "value": "Teacher:You are given an open-domain question from an open movie database. Your task is to provide an answer to that question. Try to only include the answer. Do not put it in a sentence.\nTeacher: Now, understand the problem? Solve this instance: who wrote the movie Invisible Agent?\nStudent:" }, { "from": "gpt", "value": "H.G. Wells, Curt Siodmak" } ]

[ { "from": "human", "value": "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.\nInput: 3, 4, ['1255', 'i', 'n', 'H']\nOutput:" }, { "from": "gpt", "value": "n, H" } ]

[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, we are given the script of a dialogues. Indicate if the topic of conversation is Tourism. If so, then output Yes, otherwise output No\n\nGood evening . Welcome to Mansion Hotel . I have a reservation . My name is Rodgers . Last name , Rodgers ? Yes . Very well . Welcome , Mr . Rodgers . Would you please fill out the registration card ? How are you doing today ? 0h , good . I have a long day and it's good to get here . Mr . Rodgers , how would you handle your account ? My credit card , please . I will check to see if there any messages for you ? Well , here is one message for you . Thank you . I have an 8 o ' clock appointment tomorrow morning , I would like a wake-up call . Certainly , I can take care of that for you . What time would you like the wake-up call ? 7 a . m . Mr . Rodgers , this is George . He will take care of your luggage and show you to your room . If there is anything I can do for you , please let me know . OK , I'll do that . Have a pleasant stay . \nOutput:" }, { "from": "gpt", "value": "Yes" } ]