prompt
stringlengths
26
18.1k
response
stringlengths
0
6.36k
In this task, you have to generate the named entities (NER) given its ingredients of the recipe. Named entities are the names of the items without their quantity. Ex Input: Salt, 2 (4 1/2-pound) Muscovy ducks, washed, patted dry and excess fat discarded, 1 cup soy sauce, 1/2 cup brewed coffee, 1 cup packed light brown sugar, Kona Confit Duck Stir-Fry Cashew Rice, recipe follows, Umeboshi Plum Sauce, recipe follows, 1/2 cup thinly sliced green onion tops, for garnish, 1/2 cup soy sauce, 4 teaspoons granulated sugar, 2 teaspoons toasted sesame oil, 1/4 cup peanut oil, 1 cup diced onion, 1/2 cup diced carrot, 1 teaspoon minced garlic, 1 teaspoon minced ginger, 1 teaspoon minced green onion bottoms (white part), plus 1/2 cup green onion tops, 2 cups shredded Kona confit duck leg meat, recipe follows, 7 cups cooked white rice, 1 teaspoon salt, 1/2 teaspoon fresh ground white pepper, 4 large eggs, whisked, scrambled and rough chopped, 1/2 cup frozen green peas, 1/2 cup cashews, toasted and chopped, 2 duck leg quarters, 1 tablespoon kosher salt, 2 teaspoons cracked black pepper, 1 carrot, coarsely chopped, 1 rib celery, coarsely chopped, 1 onion, coarsely chopped, 2 cups rendered duck fat, 1/2 cup brewed Kona coffee, Vegetable oil, if needed, 2 1/2 cups rice wine vinegar, 1 1/4 cups sugar, 10 Japanese pickled plums (umeboshi), drained, seeded, and chopped, 2 tablespoons minced seeded jalapeno peppers Ex Output: Salt, Muscovy, soy sauce, coffee, brown sugar, Fry, onion, soy sauce, sugar, sesame oil, peanut oil, onion, carrot, garlic, ginger, green onion, meat, white rice, salt, fresh ground white pepper, eggs, frozen green peas, cashews, quarters, kosher salt, cracked black pepper, carrot, celery, onion, coffee, Vegetable oil, rice wine vinegar, sugar, peppers Ex Input: 1 c. soft Cheddar cheese, 1 stick soft margarine, 1 c. self-rising flour, 1 c. Rice Krispies, dash of hot pepper Ex Output: Cheddar cheese, margarine, flour, Rice Krispies, pepper Ex Input: 1 mango ripe, about 15 oz, peeled, pitted and cubed, 3 teaspoons lime juice, 1 red chili pepper seeded and chopped finely, 1 pinch brown sugar, 2 avocados ripe, halved and pitted, 1 clove garlic peeled and chopped finely, 1 pinch ground cumin, 2 tablespoons hot chili paste, 6 tablespoons olive oil, 4 chicken breasts finely diced, 1 egg, 3 tablespoons breadcrumbs, 4 buns oblong, arugula for garnish Ex Output:
mango, lime juice, red chili pepper, brown sugar, avocados, clove garlic, ground cumin, hot chili paste, olive oil, chicken breasts, egg, breadcrumbs, buns, arugula
Given two noun phrases (arguments) and relationship between them, form a sentence that expresses theses arguments with the given relationship. -------- Question: Relationship: 'come to', Argument/Subject 1: 'jesus', Argument/Subject 2: 'john' Answer: Jesus had come from Galilee to be baptized by John in the Jordan River . Question: Relationship: 'be trademark of', Argument/Subject 1: 'star trek', Argument/Subject 2: 'paramount picture' Answer: Star Trek is a registered trademark of Paramount Pictures / Viacom . Question: Relationship: 'look up at', Argument/Subject 1: 'cuddy', Argument/Subject 2: 'house' Answer:
Cuddy looked up at House , This is your fault .
The input is a conversation between an automated system and a user looking for suggestions for pubs, restaurants and coffee shops in Cambridge. In the dialogue, the user may provide some criteria for the type of place they want such as price range, cuisine, etc. Given such a dialogue, output the price range the user if looking for which can take one of four values: Cheap, Moderate, Expensive and Don't Care. Output cannot be any other value than the four values. Note that if the user asks for the prices of items provided at a pub, restaurant or coffee shop but doesn't mention the price range they are looking for then the correct classification will be Don't Care. If the user does not mention a particular price, the correct classification will be Don't Care. Q: System: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?' User: 'i want to find a middle eastern restaurant i dont care about the price range' System: 'What kind of venue are you looking for? For example, a cafe, a pub, or a restaurant.' User: 'restaurant' System: 'What type of food would you like? For example, Contemporary, Fusion, or International.' User: 'middle eastern' System: 'There is no restaurant in the central area and serving middleeastern food.' User: 'i dont care about the um area' System: 'There is no restaurant in the central area and serving middleeastern food.' User: 'ok' System: 'What type of food would you like? For example, Seafood, or Vegetarian.' User: 'unintelligible eastern' System: 'What type of food would you like? For example, Japanese, Mediterranean, or Spanish.' User: 'middle eastern' System: 'There is no restaurant in the central area and serving middleeastern food.' User: 'middle eastern' System: 'There is no restaurant in the central area and serving middleeastern food.' User: 'im unintelligible' A: Don't Care **** Q: System: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?' User: 'i would like to find a greek restaurant i need the phone number and the price' System: 'What kind of price range are you looking for? For example, free, or moderate.' User: 'i dont care about the price range' System: 'What kind of price range are you looking for? For example, cheap, or moderate.' User: 'i dont care about the price range' System: 'What kind of price range are you looking for? For example, expensive, or free.' User: 'any' System: 'What kind of price range are you looking for? For example, cheap, expensive, or free.' User: 'none' System: 'What kind of price range are you looking for? For example, expensive, or moderate.' User: 'free' System: 'What kind of price range are you looking for? For example, cheap, expensive, or moderate.' User: 'free' System: 'What kind of price range are you looking for? For example, cheap, expensive, or moderate.' User: 'thank you goodbye' A: Don't Care **** Q: System: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?' User: 'sil' System: 'What kind of venue are you looking for? For example, a cafe, or a restaurant.' User: 'a cheap restaurant in the fenditton area' System: 'The Milton Park English and Thai Restaurant, which is in the Fen Ditton part of town, is a great restaurant. It's in the cheap price range.' User: 'whats the address' System: 'The Milton Park English and Thai Restaurant is located on Milton Park Golf Course, Ely Road, Milton.' User: 'whats the phone number' System: 'The phone number of the Milton Park English and Thai Restaurant is 01223864602.' User: 'whats the postal code' System: 'The Milton Park English and Thai Restaurant is in the area with the postcode CB24 6DD.' User: 'thank you goodbye' A:
Cheap ****
Given the task definition and input, reply with output. We would like you to assess the QUALITY of each of the following argument (discussing Gun Control) and determine if the argument is Valid or Invalid. A valid argument is clearly interpretable and either expresses an argument, or a premise or a conclusion that can be used in an argument for the topic of gun control. An invalid argument is a phrase that cannot be interpreted as an argument or not on the topic of gun control. And Gary Schoener, a clinical psychologist who has been diagnosing and treating clergy abuse for 28 years, told Salon.com, "There are far more heterosexual cases than homosexual."
Valid
Given the task definition and input, reply with output. You are given a sentence from a conversation between a human and a virtual assistant. Your task is to identify which one of following five services the sentence is related to - Media, Travel, Flights, Buses, RideSharing Find some great crime movies directed by Alfred hitchcock
Media
A text is given in Hindi. Translate it from the Hindi language to the Oriya language. The translation must not omit or add information to the original sentence. Ex Input: पहले विकास के लिए संपर्क एक बाधा हुआ करता था, लेकिन अब सरकार ने रेल,सड़क और वायुसेवा संपर्क को प्राथमिकता दी है। इसने भौगोलिक दूरी कम होने के चलते मनोवैज्ञानिक अवरोध को दूर किया है। Ex Output: “ପବିତ୍ର ରକ୍ଷା ବନ୍ଧନ ଅବସରରେ, ଭାରତ ଓ ବିଦେଶରେ ବସବାସ କରୁଥିବା ମୋର ଦେଶବାସୀଙ୍କୁ ମୁଁ ଅଭିନନ୍ଦନ ଓ ଶୁଭକାମନା ଜଣାଉଛି । Ex Input: नियम-कायदों की अधिसूचना जारी करने की तिथि से पहले ही यह काम आईबीबीआई को पूरा करना होगा। Ex Output: ଆଜି ଯେତେବେଳେ ଆମେ କାର୍ପେଟ କ୍ଷେତ୍ରରେ ବିଶ୍ୱର ଶୀର୍ଷ ସ୍ଥାନରେ ରହିଛୁ, ସେତେବେଳେ ଆଗାମୀ ପିଢ଼ିକୁ ଅନୁପ୍ରାଣିତ ଏବଂ ପ୍ରୋତ୍ସାହିତ କରିବା ମଧ୍ୟ ସେତିକି ଆବଶ୍ୟକ ଅଟେ । Ex Input: प्रधानमंत्री ने दृढ़तापूर्वक कहा कि जो लोग मा उमिया में भरोसा रखते हैं, वे कभी भी कन्या भ्रूण हत्या का समर्थन नहीं कर सकते। Ex Output:
ପ୍ରଧାନମନ୍ତ୍ରୀ ଦୃଢ଼ ଭାବେ କହିଥିଲେ ଯେ ଯେଉଁମାନେ ମା’ ଉମୀୟାଙ୍କଠାରେ ବିଶ୍ୱାସ କରିଥାନ୍ତି ସେମାନେ କେବେହେଲେ କନ୍ୟାଭ୍ରୂଣ ହତ୍ୟାକୁ ସମର୍ଥନ କରିବେ ନାହିଁ ।
Detailed Instructions: In mathematics, the absolute value of a number is the non-negative value of that number, without regarding its sign. For example, the absolute value of -2 is 2, and the absolute value of 5 is 5. In this task you will be given a list of numbers and you need to return the element with highest absolute value. If a negative and positive element have the same absolute value you should return the positive element. The absolute value for negative numbers can be found by multiplying them by -1. After finding the element with the maximum absolute value you should return the value of that element before you applied the absolute value. Problem:[ 11.044 3.125 19.048 -33.566 89.017 16.933 -60.11 79.186 -56.881] Solution:
89.017
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. Q: name[The Olive Grove], eatType[pub], food[Fast food], priceRange[less than £20], area[riverside], familyFriendly[no] A:
The Olive Grove is a Fast-food pub in the riverside area that has a price range of less than 20 pounds, but is not family-friendly.
Detailed Instructions: Given two noun phrases (arguments) and relationship between them, form a sentence that expresses theses arguments with the given relationship. Q: Relationship: 'open on', Argument/Subject 1: 'registration', Argument/Subject 2: 'february' A:
Registration is now open for the forthcoming test administrations on January 21 and February 10 , 2007 .
In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to generate a natural language interpretation of the given command. Here are the definitions of logical operators: 1. count: returns the number of rows in the view 2. only: returns whether there is exactly one row in the view 3. hop: returns the value under the header column of the row 4. and: returns the boolean operation result of two arguments 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column 6. nth max/nth min: returns the n-th max/n-th min of the values under the header column 7. argmax/argmin: returns the row with the max/min value in header column 8. nth argmax/nth argmin: returns the row with the n-th max/min value in header column 9. eq/not eq: returns if the two arguments are equal 10. round eq: returns if the two arguments are roughly equal under certain tolerance 11. greater/less: returns if argument 1 is greater/less than argument 2 12. diff: returns the difference between two arguments 13. filter eq/not eq: returns the subview whose values under the header column is equal/not equal to argument 3 14. filter greater/less: returns the subview whose values under the header column is greater/less than argument 3 15. filter greater eq /less eq: returns the subview whose values under the header column is greater/less or equal than argument 3 16. filter all: returns the view itself for the case of describing the whole table 17. all eq/not eq: returns whether all the values under the header column are equal/not equal to argument 3 18. all greater/less: returns whether all the values under the header column are greater/less than argument 3 19. all greater eq/less eq: returns whether all the values under the header column are greater/less or equal to argument 3 20. most eq/not eq: returns whether most of the values under the header column are equal/not equal to argument 3 21. most greater/less: returns whether most of the values under the header column are greater/less than argument 3 22. most greater eq/less eq: returns whether most of the values under the header column are greater/less or equal to argument 3 Ex Input: round_eq { sum { filter_greater_eq { all_rows ; year ; 2002 } ; laps } ; 699 } = true Ex Output: select the rows whose year record is greater than or equal to 2002 . the sum of the laps record of these rows is 699 . Ex Input: only { filter_greater { filter_eq { all_rows ; date ; september } ; attendance ; 70000 } } = true Ex Output: select the rows whose date record fuzzily matches to september . among these rows , select the rows whose attendance record is greater than 70000 . there is only one such row in the table . Ex Input: eq { hop { nth_argmax { all_rows ; commissioned ; 2 } ; name } ; chieftain } = true Ex Output:
select the row whose commissioned record of all rows is 2nd maximum . the name record of this row is chieftain .
Detailed Instructions: 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. Problem:[5, 2, 4, 6, 7, 0, 2, 3, 4, 1] Solution:
[5, 6, 7, 0, 3, 1]
Please answer the following question: Suggest a movie title for the following movie plot: The film tells the story of two Irish Catholic Fitzpatrick brothers, Mickey (Edward Burns) and Francis (Mike McGlone) and the tribulations of love, family and betrayal. Mickey is a New York City blue-collared taxi driver, unhappy over an act of infidelity committed by Heather (Cameron Diaz), his ex-fiancée. Francis is a white-collared Wall Street stock investor, who unknown to his wife, Renee (Jennifer Aniston), is having an affair. During weekends, Mickey and Francis visit their parents who live on Long Island. Their mother is never seen on screen, while they have better time interacting with their father, Frank (John Mahoney), who always gives Mickey and Francis advice to live out their lives any way they can and to always go for what drives them to succeed. While driving his cab one day, Mickey picks up Hope (Maxine Bahns), an NYU art student with whom he becomes infatuated and impulsively marries after a few days. This causes consternation for his brother, largely because he was not asked to be best man at the wedding. Mickey moves in with Hope, but later becomes disillusioned with aspects of their lifestyle, including frequent power cuts in their ramshackle apartment. Francis is also having problems in his marriage. He is concerned that he is being unfair to Heather, his mistress, the same woman Mickey left, by continuing to stay with Renee. At the same time, Renee's Italian-American family, mostly her younger sister Molly (Amanda Peet), suggest the problem with Francis' lack of interest in her is that he may be gay, so she has Mickey and their father, Frank, confront him about it. He denies being gay, but admits to being unfaithful. Meanwhile, Francis' arrogance leads him to take potshots at his brother for the apparent lack of forward progression in his life with his wife, while Francis argues with Heather about her own sexual infidelity with a much older man referred to as "Papa". One day, Mickey picks up Heather in his cab and goes up to her apartment to retrieve a television that belonged to him... Answer:
She's the One
You will be given a definition of a task first, then some input of the task. In this task, you are given music product reviews in Japanese language. The goal is to classify the review as "POS" if the overall sentiment of the review is positive or as "NEG" if the overall sentiment of the review is negative. 正直しんどい。 . GCはなまじ器用なため、あらゆるジャンルの曲を「一定のレベルで」作ることができる。だから「こんなの浮かんだ」「こんなのやってみたい」というアイデアを、比較的容易に具体化してしまえるんだろうけど、これは正直出来悪すぎ。中島みゆきと喜多郎を適当に足して二で割ったみたい。だったら中島みゆきなり喜多郎を聴けばいいわけで、GCが半端にこういった曲を作る必要は全くない。まぁメロディとサウンドをおいといても、歌詞がひどい。貧困な語彙、月並みな発想、独善的なタイトルと、AZUKI七の歌詞のまずさを総結集させたような世界になってる。AZUKIにはとにかく、その美麗なルックスに比して100万分の一のレベルでもいいからリリックセンスを磨いてほしい。 それでも★2個つけるのは、例によってカップリングが拾い物だから。特に「overblow」は、別れの清清しさとせつなさが自然に表現された、GCらしい佳曲。 Output:
NEG
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task. Indicate with `Yes` if the given question involves the provided reasoning `Category`. Indicate with `No`, otherwise. We define five categories of temporal reasoning. First: "event duration" which is defined as the understanding of how long events last. For example, "brushing teeth", usually takes few minutes. Second: "transient v. stationary" events. This category is based on the understanding of whether an event will change over time or not. For example, the sentence "he was born in the U.S." contains a stationary event since it will last forever; however, "he is hungry" contains a transient event since it will remain true for a short period of time. Third: "event ordering" which is the understanding of how events are usually ordered in nature. For example, "earning money" usually comes before "spending money". The fourth one is "absolute timepoint". This category deals with the understanding of when events usually happen. For example, "going to school" usually happens during the day (not at 2 A.M). The last category is "frequency" which refers to how often an event is likely to be repeated. For example, "taking showers" typically occurs ~5 times a week, "going to Saturday market" usually happens every few weeks/months, etc. Sentence: Jack played basketball after school, after which he was very tired. Question: How long did Jack play basketball? Category: Event Duration. Solution: Yes. Why? The question asks about the duration of playing basketball, therefore it's a "event duration" question. New input: Sentence: The NMCC learned about United 93 from the White House. Question: Is United 93 still operational? Category: Transient v. Stationary. Solution:
No.
You are given a list of integers and an integer target, return a list of a pair of numbers in any order such that they add up to target. If there is no such pair of numbers, then return an empty list Input: Consider Input: [34, 25, 36, 40, 21, 2, 12, 32, 16, 13, 18, 17, 28, 1, 33, 26, 38, 4, 37, 49], target=82 Output: [33, 49] Input: Consider Input: [17, 22, 14, 32, 31, 47, 33, 25, 12, 24, 45, 3, 35, 41, 46, 34, 42, 30, 43, 19], target=47 Output: [14, 33] Input: Consider Input: [42, 41, 13, 46, 15, 28, 38, 29, 45, 35, 37, 9, 16, 18, 30, 14, 26, 7, 12, 48], target=20
Output: [13, 7]
In this task you are given a tweet that contains some form of irony. You must classify the type of irony the tweet has. Label the tweets ("polarity","situational","other") based on the irony they have. Situational irony happens when a situation fails to meet some expectations, Label these instances as "situational". polarity irony happens when irony is achieved by inverting the intended sentence, Label these instances as "polarity". There are other kinds of ironies that are neither polarity nor situational, Label these instances as "other". Note that URLs in the text have been replaced with [Link]. Can anyone tell iv been uploading items onto depop today lol #lotsofdepopuploaded other I'm glad H & M has employed enough staff today. #nohelp #terrible polarity On my TL I see a Somerholic that unfollowed me tweeting retweet if you're a Somerholic to see how many are there.also i'm not allowed
situational
In this task, you are given a date in "dd/mm/yyyy" format. You need to check if the date is valid or not. Return 1 if it is valid, else return 0. A date is valid if the components day("dd"), month("mm") and year("yyyy") are all valid individually. A day(dd) is valid if it: a) lies between 1 and 31 for the months of January, March, May, July, August, October, December, b) lies between 1 and 28 for February on non-leap years and between 1-29 on leap years, c) lies between 1-30 for all other months. A month(mm) is valid if it lies in the range from 1 to 12 as there are 12 months in a year. A year is always valid if it is expressed in the form of "yyyy". 27/10/1485
1
Given the task definition and input, reply with output. You will be given a context and a verb separated with a newline character, and you have to answer if the given verb is static or not. We say a verb is static if it is about an event that doesn't change or it happens regularly. The output should be "Yes" if the verb is static and "No" otherwise. CBS News first reported last night that the tomb may contain the remains of Air Force pilot Michael Blassie. There was a suspicion the body (was) Blassie because his uniform and ID card were found near the body in Vietnam. Verb: was
Yes
Given a sentence in the Japanese and Filipino language. Your task is check if the Filipino sentence is translation of Japanese. if the translation is correct than generate label "Yes", otherwise generate label "No". [EX Q]: Japanese: そのモデルのトレント900エンジンに関して、”ロールスロイス、エアバスと親密に話し合いを重ね”、テストが実行されたことをスポークスマンは確認した。 Filipino: Bumagsak malapit sa Belgrade, Serbia, nuong martes ang isang Mig-29 na eroplanong pangdigma ng Pwersang Panghimpapawid ng Serbia at ng Depensang Panghimpapawid. [EX A]: No [EX Q]: Japanese: オーストラリアは今年、161人の選手をパラリンピックに出場させる。 Filipino: Ang mga kinatawan ay pinaputukan ng mga baril pero wala sinumang nasaktan, sabi ng pulisya. [EX A]: No [EX Q]: Japanese: フォックスコンは調査のために生産を停止して「影響を受けた作業場ではすべての作業が停止されており、同様の加工機能を実施する他のすべての作業場での生産も調査結果が出るまで停止される」と言った。 Filipino: Pinatigil ng Foxconn ang produksyon upang mag-imbestiga, na sinasabing "Mananatiling nakahinto ang operasyon sa naapektuhang gawaan at ang paggawa sa lahat ng ibang mga gawaang nagsasagawa ng katulad ng mga ginagawang tungkulin ay pinatigil din upang tapusin ang mga resulta ng imbestigasyon." [EX A]:
Yes
Detailed Instructions: In this task, you will be given a debate topic, along with a sentence from the debate. You should classify the given sentence and choose the type of that sentence. Possible types are explained below. Policy: This refers to a sentence proposing a specific course of action to be taken. It typically contains modal verbs like "should" and "ought to". It cannot be directly proved with objective evidence, and a proper type of support is a logical reason from which the proposition can be inferred. Value: This refers to a sentence containing value judgments without making specific claims about what should be done (If so, then it is a Policy sentence.). Because of the subjectivity of value judgments, it cannot be proved directly with objective evidence. Fact: This refers to an objective proposition expressing or dealing with facts or conditions as perceived without distortion by personal feelings, prejudices, or interpretations. A Fact sentence has a truth value that can be verified with objective evidence that may be available at the time the claim is made; predictions about future are considered unverifiable. Testimony: This refers to an objective sentence about the author's personal state or experience. Evidence for Testimony is not publicly available in most cases. Problem:topic: NON VOTING IN ELECTIONS MUST BE TAKEN SERIOUSLY sentence: I'm sorry, but this idea cannot be taken seriously. Solution:
Value
In this task, you are given the name of an Indian food dish. You need to classify the dish as "sweet" or "spicy". Example: Keerai poriyal Example solution: spicy Example explanation: Keerai poriyal is spicy in flavor Problem: Handwo
Solution: spicy
Q: In this task, you are given the abstract of a research paper. Your task is to generate a summary of this abstract. Your summary should not be very short, but it's better if it's not more than 30 words. In many real-world settings, a learning model must perform few-shot classification: learn to classify examples from unseen classes using only a few labeled examples per class. Additionally, to be safely deployed, it should have the ability to detect out-of-distribution inputs: examples that do not belong to any of the classes. While both few-shot classification and out-of-distribution detection are popular topics, their combination has not been studied. In this work, we propose tasks for out-of-distribution detection in the few-shot setting and establish benchmark datasets, based on four popular few-shot classification datasets. Then, we propose two new methods for this task and investigate their performance. In sum, we establish baseline out-of-distribution detection results using standard metrics on new benchmark datasets and show improved results with our proposed methods. A:
We quantitatively study out-of-distribution detection in few-shot setting, establish baseline results with ProtoNet, MAML, ABML, and improved upon them.
In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the count of all the alphabetical elements in the given list. Return 0 if no alphabetical element in the list Ex Input: ['q', '9775', 'Z', 'h', 'e', '6595', '5249', '3453', 'E', '4499'] Ex Output: 5 Ex Input: ['f', '9403', 'g', 'J', 'q', 'T', 'O', '8619', '6269', '9231', '3769', 'M', 'n', 'I', 'e', 'r', 'K', 'D', 'x', '7341'] Ex Output: 14 Ex Input: ['4379', 'H', '7827', 'D', '1207', '9663', '3473', '5175', 'y', '6503', '8123', 'T', '7973', '5921', '8019', '4743', 'G', 'U', 'V', 'J', 'u', '4633', 'h', '1201'] Ex Output:
10
Detailed Instructions: In this task, you're given text messages in natural language. Your task is to classify those text messages based on their content into two classes: (1) Spam and (2) Ham messages. If the content of the given message is irrelevant to the receiver or is equally relevant to many other potential recipients then it must be labeled as ‘spam’, otherwise, it should be labeled as ‘ham’. Problem:Your account has been refilled successfully by INR <DECIMAL> . Your KeralaCircle prepaid account balance is Rs <DECIMAL> . Your Transaction ID is KR <#> . Solution:
ham
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task. In this task, you are given an english sentence and a kurdish sentence you have to determine if they both are faithful translations of each other. Construct an answer that is 'Yes' if the second 'Kurdish' sentence is a translation of 'English' sentence and 'No' otherwise 'English : Diyarbakır 2nd Criminal Court of Peace has issued a gag order on the bomb attack on police shuttle in Diyarbakır.', 'Kurdish : Biryara qedexekirinê di rûpela Lijneya Bilnd a Radyo û Televizyonan (RTUK) de bi daxuyaniyek hat diyarkirin û wiha hat gotin:' Solution: Yes Why? The answer is 'Yes' because the second sentence is a consise and faithful translation of 'English' sentence into 'Kurdish' New input: 'English : — garo paylan (@GaroPaylan) 18 Mayıs 2016','Kurdish : — garo paylan (@GaroPaylan) 18 Mayıs 2016' Solution:
Yes
Part 1. Definition Classify the given hotel review based on the sentiment it expresses into two classes: negative and positive. Part 2. Example I stayed at the Hilton Chicago for my cousins wedding. The service was impeccable. Not only was the staff attentive, they were respectful and careful not to interrupt the guests or make themselves known when serving dinner. I had the chicken wellington and it was to die for! The chicken was perfect and moist but the pastry crust was flaky and crispy. They even had Pakistani dinner options for some of the guests. The amenities were great, and after an open bar the night before, the Mimosas and brunch buffet couldn't have been better! I would love to have my wedding there. Answer: positive Explanation: Review writer likes the hotel. There are strong positive words like 'impeccable' and 'great'. Therefore it is classified as a positive review. Part 3. Exercise This is a great hotel! The views are fabulous, the service it friendly and the location is superb. We booked a room on an upper floor and had access to the lounge where breakfast and snacks were available with picture perfect views of the Chicago River. The only negative is that the ceilings in the hall and room are low and can make you feel a little cramped. We booked our room for $89 a night for Memorial Day weekend. It was a steal! I highly recommend this hotel to anyone and will be returning! Answer:
positive
In this task you will be given a list of integers. You should find the minimum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one integer subtracted by another. The output should be a single integer which is the smallest possible absolute distance. Example input: [9, 40, -33, 12, 17, -32, 40] Example output: 0 Example explanation: The minimum absolute difference is 0 because '40 - 40 = 0' and '40' appears in the list twice. So this is a good example. Q: [-57, 19, -76, -32, 94, 26] A:
7
Detailed Instructions: In this task, you will be shown an English sentence. You need to classify the sentence as either a representation of an adjunct island or as an incorrect representation. A correct representation should be denoted as 'good' while everything else should be denoted as 'bad'. A correct representation of an adjunct island will be a grammatically correct instance of a sentence using an adjunct island. An incorrect representation will be everything else. See one example below: Problem: Who should the boss fire after seeing HR? Solution: good Explanation: The sentence forms an adjunct island. Problem: What had Cynthia messed up after taking some couch? Solution:
good
TASK DEFINITION: Given a text passage as input consisting of dialogues of negotiations between a seller and a buyer about the sale of an item, the task is to classify the text into one of the labels from the two possible outputs - 'accepted'/'rejected'. Select [accepted] if by the end of the conversation the buyer seems likely to buy the item from the seller. A sale is likely made when the buyer and seller agree upon a common price or when a deal is made between them. Select [rejected] if the buyer did not seem interested in buying the item from the seller at the end of the conversation. This happens when the buyer and seller do not agree on the price or other aspects of the item being sold by the seller. PROBLEM: Buyer: hello Seller: Hello. Are you interested in our services? Buyer: Yes I am Seller: Ok. We charge $50 for unlocking and flashing phone devices. Buyer: That much. Are you willing to discount the price for first time customers Seller: For first time customers we offer a price of $45 for the service. Buyer: That's still pretty steep..Hmm what about 35.00? Seller: Sorry, I can not go that low. The best I could do is $45 and have the device back to you within 30 minutes. Seller: Buyer: What other services do I get with 45.00? Seller: There are no other services? We unlock and flash phones to remove them from the network--that's what we do. Buyer: If you are flashing my phone I still have to pay for first month service. You are not losing anything with 35.00. I still have to pay for first month service. Seller: I can make you a final offer of $45 to which you can accept or reject. Sorry, our prices are firm. Buyer: Do I get a free phone case with it? What about 40.00? Seller: I do not see us reaching an agreement here. Seller: SOLUTION: rejected PROBLEM: Buyer: I am very interested in the bike you have for sale. Could you give me some information about it? Seller: Hi there, I sure can. I ride semi-professional and I was recently sponsored, so they have me riding their brand now, I'm selling this one. I've taken great care of it, loads of upgrades from the stock model. Only weighs about 8 pounds. Buyer: That sounds very nice. I am very interested, except I am a bit strapped for cash right now. I would like to offer you $1900 for it. That is cash in hand and I will pick it up today. Seller: I could maybe do that if you have anything you could throw in. Do you have any bike parts maybe? I just popped a wheel actually Buyer: I have a wide assortment of various tires and wheels. Why don't you run the bike by, and you can pick out a couple tires or wheels to go in with the offer. Seller: Sounds perfect, I'll run the bike out to you tonight and we'll do the deal for 1900, sound good? Buyer: Sounds great. Buyer: Seller: SOLUTION: accepted PROBLEM: Buyer: Hi are these still available? Seller: yes they are ,Would you be willing to give me $80 for the 2 tables that's only $40 each Buyer: Well you've listed the item as 50 how come you're asking for 80? Seller: oh sorry, I have multiple items listed I got this one confused you are correct, I am asking $50 for the 2 tables Buyer: No worries. I still think its too much for it. Is there any room for negotiation? Seller: Yes I am willing to negotiaate Buyer: can you accept 25 for them and I am willing to come pick it up myself today itself and pay you right away? Seller: How about we go middle ground , how does $35 sound? and I can help you load them in your vehicle. Buyer: is this new or used? Seller: They are used but in like new conditon Buyer: how does 30 sound? Please? Pretty please? Seller: I really can't go to low due to it being 2 tables and being in like new conditon, it is almost like getting 2 new tables I promise. Buyer: Okay then 35 will do! Seller: awesome it's a deal. Seller: Buyer: SOLUTION:
accepted
TASK DEFINITION: Given a sentence in Japanese, provide an equivalent paraphrased translation in Chinese that retains the same meaning both through the translation and the paraphrase. PROBLEM: Laetitia Pujolは、Manとしての恥ずべき存在でした。カール・パケットは彼の強くて憂うつなダブルでした。そしてマシュー・ガニオは女を描いた。 SOLUTION: Laetitia Pujol是一个阴暗的存在,因为The Man,Karl Paquette是他强壮,忧郁的双重,而Mathieu Ganio描绘了The Woman。 PROBLEM: 1951年、彼は1956年に死去しました。 SOLUTION: 他于1951年去世,并于1956年退休。 PROBLEM: 1998年のフレッドミラーと2000年のジョンポールミラーの死後、メアリーミラーはクリーブランドの南に位置する家に住み続けた。 SOLUTION:
弗雷德米勒于1998年去世,约翰保罗米勒于2000年去世,玛丽米勒继续住在克利夫兰南部的房子里。
Teacher:In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to classify the command into one of these seven categories: (1) majority, (2) unique, (3) superlative, (4) count, (5) comparative, (6) aggregation, and (7) ordinal. Here are the defications of each category: 1. majority: Describing the majority values (most or all) over one column, with the scope of all table rows or a subset of rows 2. unique: Describing one unique row, regarding one column, with the scope of all table rows or a subset of rows 3. Superlative: Describing the maximum or minimum value in a column, with the scope of all table rows or a subset of rows 4. Ordinal: Describing the n-th maximum or minimum value in a column, with the scope of all table rows or a subset of rows 5. Comparative: Comparing two rows in the table, regarding their values in one column 6. Count: counting some rows in the table based on the values in one column, with the scope of all table rows or a subset of rows 7. Aggregation: Describing the sum or average value over a column, with the scope of all table rows or a subset of rows. Here are the definitions of logical operators for understanding of command: 1. count: returns the number of rows in the view. 2. only: returns whether there is exactly one row in the view. 3. hop: returns the value under the header column of the row. 4. and: returns the boolean operation result of two arguments. 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. 7. argmax/argmin: returns the row with the max/min value in header column. 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. 9. eq/not_eq: returns if the two arguments are equal. 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. 11. greater/less: returns if the first argument is greater/less than the second argument. 12. diff: returns the difference between two arguments. 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. 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. 16. filter_all: returns the view itself for the case of describing the whole table 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. 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. Teacher: Now, understand the problem? Solve this instance: and { only { filter_eq { all_rows ; venue ; nuremberg } } ; eq { hop { filter_eq { all_rows ; venue ; nuremberg } ; date } ; 3 june 2000 } } Student:
unique
Q: Creating a multiple-choice question from the given context and a 'group' which indicate the focus of the question. The question must come first, separated by <sep> from the candidate answers. The answer to the question does not have to exist in the context. context: A person drops a coin, a bottle, a plate, and a mirror from a balcony.<sep>group: breaking A:
question: Which object is the least likely to break?<sep>A: coin<sep>B: bottle<sep>C: plate<sep>D: mirror
You will be given a text in Russian language which contain different emotion labels from the list - ['joy', ' sadness', 'surprise', 'fear', 'anger']. You need to output the incorrect emotion label, which is irrelevant to the input text. Your answer (i) should contain only one emotion label (ii) should be unambiguous. One example: Но мне ужасно грустно , и плохо. Solution is here: surprise Explanation: The input text states 'But I'm terribly sad and bad'. There is an emotion of 'sadness' in the input text. So, 'surprise' is an incorrect emotion label. Now, solve this: А тут уже я не хочу ловить на себе странные взгляды ... И уляпанные вусмерть футболки стирать потом мне . Solution:
surprise
In this task, you are given an input stream, and your task is to produce a grammatically correct version of the input sentence. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a grammatically correct version of the input stream. Stream words are in [] and have been separated with a comma. The sentence can contain words that have case, punctuation, stem-based, intra-word, and digit punctuation errors that need to be corrected. For example, the text should be uppercased/lowercased as per necessity (like the beginning of a sentence, proper nouns, etc.), and digits need to be normalized (6 as six and so on). Note that you don't need to normalize the years. You don't need to fully edit the sentences, if end of the input stream contains sentence fragments, keep them as is. [EX Q]: ['in', 'ancient', 'Greece', 'people', 'did', 'not', 'use', 'soap', 'and', 'water', 'to', 'wash', 'they', 'used', 'oil', 'and', "we're", 'seeing', 'a', 'sculpture', 'called', 'the', 'scraper', 'or', 'the', 'epoxy', 'minos', 'by', 'lysippos', 'which', 'shows', 'just', 'that', 'this', 'is', 'an', 'athlete', 'whose', 'body', 'is', 'now', 'covered', 'with', 'perspiration', 'and', 'dust', 'and', 'what', "he's", 'doing', 'is', "he's", 'washing', 'himself', 'first', 'by', 'covering', 'his', 'body', 'with', 'oil', 'and', 'then', 'using', 'Astral', 'to', 'scrape', 'all', 'of', 'the', 'grime', 'off', 'with', 'the', 'oil', 'lysippos', 'was', 'one', 'of', 'the', 'most', 'famous', 'sculptors', 'from', 'the', 'fourth', 'century', 'BCE', 'but', 'of', 'course', "we're", 'not', 'looking', 'at', 'the', 'actual', 'work', 'by', 'lysippos'] [EX A]: ['in', 'ancient', 'Greece,', 'people', 'did', 'not', 'use', 'soap', 'and', 'water', 'to', 'wash,', 'they', 'used', 'oil.', 'And', "we're", 'seeing', 'a', 'sculpture', 'called', 'the', '"Scraper"', 'or', 'the', 'epoxy', 'minos', 'by', 'Lysippos,', 'which', 'shows', 'just', 'that.', 'This', 'is', 'an', 'athlete', 'whose', 'body', 'is', 'now', 'covered', 'with', 'perspiration', 'and', 'dust.', 'And', 'what', "he's", 'doing', 'is', "he's", 'washing', 'himself,', 'first', 'by', 'covering', 'his', 'body', 'with', 'oil,', 'and', 'then', 'using', 'Astral', 'to', 'scrape', 'all', 'of', 'the', 'grime', 'off', 'with', 'the', 'oil', 'lysippos', 'was', 'one', 'of', 'the', 'most', 'famous', 'sculptors', 'from', 'the', 'fourth', 'century', 'BCE.', 'But,', 'of', 'course,', "we're", 'not', 'looking', 'at', 'the', 'actual', 'work', 'by', 'Lysippos'] [EX Q]: ['hi', 'this', 'is', 'Kim', 'from', 'Khan', 'Academy', 'today', "we're", 'learning', 'more', 'about', 'the', 'takings', 'Clause', 'of', 'the', 'Fifth', 'Amendment', 'in', 'another', 'video', "we'll", 'discuss', 'the', 'other', 'clauses', 'of', 'the', 'Fifth', 'Amendment', 'those', 'that', 'deal', 'with', 'self-incrimination', 'and', 'due', 'process', 'of', 'law', 'but', 'in', 'this', 'video', "we're", 'concentrating', 'on', 'just', 'the', 'last', 'few', 'words', 'of', 'the', 'Fifth', 'Amendment', 'which', 'forbid', 'the', 'government', 'from', 'taking', 'private', 'property', 'for', 'public', 'use', 'without', 'just', 'compensation', 'to', 'learn', 'more', 'about', 'the', 'takings', 'Clause', 'I', 'sought', 'out', 'the', 'help', 'of', 'two', 'experts', 'Richard', 'Epstein', 'is', 'the', 'Lawrence', 'a', 'Tisch', 'professor', 'of', 'law', 'and', 'director', 'of', 'the'] [EX A]: ['hi', 'this', 'is', 'Kim', 'from', 'Khan', 'Academy.', 'Today', "we're", 'learning', 'more', 'about', 'the', 'takings', 'clause', 'of', 'the', 'Fifth', 'Amendment.', 'In', 'another', 'video,', "we'll", 'discuss', 'the', 'other', 'clauses', 'of', 'the', 'Fifth', 'Amendment,', 'those', 'that', 'deal', 'with', 'self-incrimination', 'and', 'due', 'process', 'of', 'law', 'but', 'in', 'this', 'video,', "we're", 'concentrating', 'on', 'just', 'the', 'last', 'few', 'words', 'of', 'the', 'Fifth', 'Amendment', 'which', 'forbid', 'the', 'government', 'from', 'taking', 'private', 'property', 'for', 'public', 'use', 'without', 'just', 'compensation.', 'To', 'learn', 'more', 'about', 'the', 'takings', 'clause,', 'I', 'sought', 'out', 'the', 'help', 'of', 'two', 'experts.', 'Richard', 'Epstein', 'is', 'the', 'Laurence', 'A.', 'Tisch', 'professor', 'of', 'law', 'and', 'director', 'of', 'the'] [EX Q]: ['the', 'point', 'negative', '8', 'comma', '5', 'is', 'reflected', 'across', 'the', 'y-axis', 'plot', 'negative', '8', 'comma', '5', 'and', 'its', 'reflection', 'across', 'the', 'y-axis', 'so', 'first', "let's", 'plot', 'negative', '8', 'comma', '5', 'so', 'its', 'x-coordinate', 'is', 'negative', '8', 'so', "I'll", 'just', 'use', 'this', 'one', 'right', 'over', 'here', 'so', 'the', 'x-coordinate', 'is', 'negative', '8', 'and', 'the', 'y-coordinate', 'is', '5', 'so', "I'll", 'go', 'up', '5', 'so', 'the', 'y-coordinate', 'is', '5', 'right', 'over', 'here', 'you', 'see', 'negative', '8', 'and', '5', "we've", 'gone', '8', 'to', 'the', 'left', 'because', "it's", 'negative', 'and', 'then', "we've", 'gone', '5', 'up', 'because', "it's", 'a', 'positive', '5', 'so', "we've", 'plotted', 'negative', '8'] [EX A]:
['The', 'point', 'negative', '8', 'comma,', '5', 'is', 'reflected', 'across', 'the', 'y-axis.', 'Plot', 'negative', '8', 'comma', '5', 'and', 'its', 'reflection', 'across', 'the', 'y-axis.', 'So', 'first', "let's", 'plot', 'negative', '8', 'comma', '5.', 'So', 'its', 'x-coordinate', 'is', 'negative', '8,', 'so', "I'll", 'just', 'use', 'this', 'one', 'right', 'over', 'here.', 'So', 'the', 'x-coordinate', 'is', 'negative', '8,', 'and', 'the', 'y-coordinate', 'is', '5,', 'so', "I'll", 'go', 'up', '5.', 'So', 'the', 'y-coordinate', 'is', '5', 'right', 'over', 'here.', 'You', 'see', 'negative', '8', 'and', '5.', "We've", 'gone', '8', 'to', 'the', 'left', 'because', "it's", 'negative,', 'and', 'then', "we've", 'gone', '5', 'up,', 'because', "it's", 'a', 'positive', '5.', 'So', "we've", 'plotted', 'negative', '8']
In this task, you will be given a sentence about a person. You should determine how the sentence affects how the person is perceived by most people in society. Your choices are: Positive: The social perception of [PERSON] in the sentence is considered predominantly positive. Negative: The social perception of [PERSON] in the sentence is considered predominantly negative. No impact: There is no clear impact of social perception of [PERSON] associated with the sentence. Example Input: [PERSON] had a part-time job as a police officer, and he had never been convicted of a crime. Example Output: Positive Example Input: [PERSON] started working as a courier for the company and soon became a part of the company's infrastructure, as well as a member of the company's staff. Example Output: Positive Example Input: [PERSON] was described as "a young, white male" and had "a strong personality and strong intellect. Example Output:
Positive
In this task, you will be given a list of numbers. The goal is to divide all the numbers in the list by a constant such that the sum of the resulting list is 1. The output should be rounded to 3 decimals. Let me give you an example: [1, 2, 3] The answer to this example can be: [0.167, 0.333, 0.500] Here is why: The output list sums to 1.0 and has the same weight as the input 0.333 is twice as large as 0.167, .5 is 3 times as large as 0.167, and 0.5 is 1.5 times as large as 0.333. This is a good example. OK. solve this: [246.183, 41.271, 148.968] Answer:
[0.564 0.095 0.341]
Given the task definition and input, reply with output. Given a sentence in Korean, provide an equivalent paraphrased translation in Spanish that retains the same meaning both through the translation and the paraphrase. 이 시리즈는 Wal-Mart Canada 만 독점적 이었지만 Spawn Store에서 온라인으로 판매되었습니다.
Esta serie fue exclusiva de Wal-Mart Canadá, pero finalmente se vendió en la Tienda Spawn en línea.
Given the task definition and input, reply with output. Given a pair of words, deduce the type of relationship between them. The various types of relations are: 'HYPER', 'COORD' and 'RANDOM'. Let's denote the first word by X and the second word by Y. A COORD relationship holds when X and Y belong to the same semantic class. A HYPER relationship applies when X is a specific instance of Y. If niether COORD nor HYPER are applicable then the relationship is RANDOM. X: whale, Y: rabbit
COORD
You will be given a definition of a task first, then some input of the task. You are given a set of queries separated by ' ', and your job is to find out the query which is not a well-formed or well-structured query in terms of grammar, punctuations, or spelling errors. Does miley cyrus have 1 billion dollars ? How do you check a unijunction transistor ? Nissan micra 2003 ignition barrel wo n't turn ? Where are ringtails found ? Output:
Nissan micra 2003 ignition barrel wo n't turn ?
Given a sentence in Igbo language, translate the sentence to English language keeping the meaning of the original sentence intact [EX Q]: Igbo sentence: Ị chọrọ igwu egwu sinima n'Ịntanet? Anyị ga-agwa gị otu esi eme nke a - ntụziaka site na nkwụsị ụkwụ; [EX A]:   Do you want to play online casino? We will tell you how to do this – step-by-step instructions; [EX Q]: Igbo sentence: Lee anya na amaokwu isii. [EX A]: Look at verse six. [EX Q]: Igbo sentence: 6 Moses we ziga ha, nnù ndikom abua na ọgu iri nke ebo ọ bula, isoro usu-ndi-agha, ha na Finehas nwa Eleeza, bú onye-nchu-àjà, isoro usu-ndi-agha, ihe nile nke ebe nsọ Chineke na opì abua ọ gāfù idasi uda ike di kwa n'aka-ya. [EX A]:
6 And Moses sent them to the war, a thousand of every tribe, them and Phinehas the son of Eleazar the priest, to the war, with the holy instruments, and the trumpets to blow in his hand.
You will be given a definition of a task first, then some input of the task. Given two entities as input, classify as "yes" if second entity is the part of the first entity. Otherwise classify them as "no". These are entities of meronym In linguistics, meronymy is a semantic relation between a meronym denoting a part and a holonym denoting a whole. In simpler terms, a meronym (i.e., second entity) is in a part-of relationship with its holonym (i.e., first entity). Entity 1: carnivore Entity 2: intestine Output:
yes
Detailed Instructions: In this task you will be given a list of integers. A list contains numbers separated by a comma. You need to round every integer to the closest power of 2. A power of 2 is a number in the form '2^n', it is a number that is the result of multiplying by 2 n times. The following are all powers of 2, '2, 4, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096'. If an integer is exactly in equally far from two different powers of 2 then you should output the larger power of 2. The output should be a list of integers that is the result of rounding each integer int the input list to the closest power of 2. The output should include a '[' to denote the start of the output list and ']' to denote the end of the output list. See one example below: Problem: [16, 205, 171, 2, 9, 317] Solution: [16, 256, 128, 2, 8, 256] Explanation: Every integer in the input list is rounded to the nearest power of 2. The number 2 and 16 are in the input list and both are a power of 2, therefore rounding to the closest power of 2 returns the same number. This is a good example. Problem: [193, 186, 4292, 1325, 21, 46, 3, 156, 1185, 4042, 2360, 20, 41] Solution:
[256, 128, 4096, 1024, 16, 32, 4, 128, 1024, 4096, 2048, 16, 32]
Q: The provided file includes inquiries about restaurants, and we ask you to translate those to the Finnish language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are *NOT* looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 *SHOULD NOT* be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for fully capitalized special placeholders (e.g. NUMBER, DATE, TIME). Please do the same in your translations. search for " chipotle " A:
etsi " chipotle "
In this task you will be given a string of characters. You should remove all vowels from the given string. Vowels are: i,e,a,u,o. The character 'y' or 'Y' does not count as a vowel. Ex Input: JSoOvy Ex Output: JSvy Ex Input: UEUKlygAQovYIXkTAhq Ex Output: KlygQvYXkThq Ex Input: ntRlUeaofBAUoXyozyI Ex Output:
ntRlfBXyzy
Q: In this task, you need to remove all words of a given length in the sentence. The number of letters in a word determine its length, for example, the length of the word "apple" is 5. Sentence: 'an open laptop sits on a table next to some candlesticks'. Remove all words of length '5' in the given sentence. A:
an open laptop sits on a next to some candlesticks
Instructions: In this task, you are given an english sentence and a kurdish sentence you have to determine if they both are faithful translations of each other. Construct an answer that is 'Yes' if the second 'Kurdish' sentence is a translation of 'English' sentence and 'No' otherwise Input: 'English : Now Turkey has made some progress and the health system has also improved which means that one now goes to hospitals to socialize and “search for girls” apparently. A woman partner is something you hand-pick like vegetables in a greengrocer anyway. And they are on stand-by, waiting in the hospital and men come and pick them.','Kurdish : Min ji xwe re fikirî ka çawa dikare ev tişt çêbibe. Pênc sal in ez her meh raporan çêdikim û tiştên hatin bîra min ev in.' Output:
No
Given the task definition and input, reply with output. In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are "this national park", "this dog breed", and "this president", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question. Is this dog breed not hypoallergenic? Does this dog breed always have spots?
Does this dog breed shed frequently or have spots on their coat?
Definition: In this task, you're given a sentence and question. Based on the information provided in a given sentence, you should identify the shortest continuous text span from the sentence that serves as an answer to the given question. Answer the question using coreference resolution. Coreference resolution is the task of clustering mentions in text that refer to the same underlying real world entities. For example let's take a sentence 'I voted for Obama because he was most aligned with my values, she said.' Here in this example 'I', 'my', and 'she' belong to the same cluster and 'Obama' and 'he' belong to the same cluster. Now let's discuss another example , original sentence: 'I voted for Trump because he was most aligned with my values',John said. Now here is the same sentence with resolved coreferences: 'John voted for Trump because Trump was most aligned with John's values',John said. Input: Sentence: Elizabeth moved her company from Sparta to Troy to save money on taxes; the taxes are much lower there. Question: Where are the taxes lower? Output:
Troy
Given a sentence in Bulgarian, generate a new Bulgarian 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. [Q]: Най-вероятно ще се запознаете със съпруг, който се грижи за него в банята. [A]: Вие сте вероятна да намерите някой, който да се грижи за кожата в банята. [Q]: Най-вероятно ще намерите врата, заключена в затвора. [A]: Нима ще се качите на врата, заключена в затвора? [Q]: Най-вероятно ще надушите чувал в самолет. [A]:
Възможно е да вземете чанта с летателен апарат в самолет.
Detailed Instructions: You will be given a context and a verb separated with a newline character, and you have to answer if the given verb is static or not. We say a verb is static if it is about an event that doesn't change or it happens regularly. The output should be "Yes" if the verb is static and "No" otherwise. Q: It strongly condemns the terrorist bomb attacks. And it stresses that every nation has the duty to refrain from organizing, instigating, assisting or (participating) in terrorist acts in another state. Verb: participating A:
No
Read the given story and classify it as 'imagined', 'recalled', or 'retold'. If a story is imagined, the person who wrote the story is making it up, pretending they experienced it. If a story is recalled, the person who wrote the story really experienced it and is recalling it from memory. If a story is retold, it is a real memory like the 'recalled' stories, but written down much later after previously writing a 'recalled' story about the same events. So, recalled stories and retold stories will be fairly similar, in that they both were real experiences for the writer. Imagined stories have a more linear flow and contain more commonsense knowledge, whereas recalled stories are less connected and contain more specific concrete events. Additionally, higher levels of self reference are found in imagined stories. Between recalled and retold stories, retold stories flow significantly more linearly than recalled stories, and retold stories are significantly higher in scores for cognitive processes and positive tone. One example: Concerts are my most favorite thing, and my boyfriend knew it. That's why, for our anniversary, he got me tickets to see my favorite artist. Not only that, but the tickets were for an outdoor show, which I love much more than being in a crowded stadium. Since he knew I was such a big fan of music, he got tickets for himself, and even a couple of my friends. He is so incredibly nice and considerate to me and what I like to do. I will always remember this event and I will always cherish him. On the day of the concert, I got ready, and he picked me up and we went out to a restaurant beforehand. He is so incredibly romantic. He knew exactly where to take me without asking. We ate, laughed, and had a wonderful dinner date before the big event. We arrived at the concert and the music was so incredibly beautiful. I loved every minute of it. My friends, boyfriend, and I all sat down next to each other. As the music was slowly dying down, I found us all getting lost just staring at the stars. It was such an incredibly unforgettable and beautiful night. Solution is here: imagined Explanation: This is a good example because it really was an imagined story. The attributes that should tip you off are that the story is light on concrete events (they describe things in broad terms such as going to a restaurant and being at the stadium, but nothing specific about who was exactly where and anything specifically notable someone said or did) and heavy on references to the writer themselves and their internal feelings (they frequently repeat how much they loved it, how romantic they felt, how they cherished the night, etc). It's also very linear and structured, pointing to this being an imagined story. Additionally, the events and feelings described seem a little romanticized or idealized beyond what is usually a realistic circumstance. Now, solve this: I continue to be going through a divorce. Previously I discussed how my ex spouse was court ordered to make my car payment. He didn't and my car was repossessed. We later went to court because he was in contempt/ violation of the court order. He basically got a slap on the hand. Fast forward to today. He continues to be responsible for the same bills, minus that specific car payment and now had to make a car payment on another car. He has failed to make any kind of payment in the last 3 months, not even child support. The divorce has taken over a year to finalize. I don't see an end in site. His attorney recently requested to be dismissed from his case. I guess my ex thinks he is above the law. We will see if he gets a slap on the hand this time. He is of course, in contempt again. We will have a trial scheduled. Solution:
retold
Instructions: You're given a sentence and your task is to classify whether the sentence is acceptable or not. Any sentence which is grammatically correct, has a naturalistic text, is written by a native speaker and which minimizes superfluous content is acceptable, otherwise unacceptable. If the sentence is acceptable then write "acceptable", otherwise "unacceptable". Input: Steve tossed the ball. Output:
acceptable
Definition: In this task, you are given a country name and you need to return the barcode prefix of the given country. A barcode prefix is a 3-digit number at the begining of all the barcodes on products from a company or country. Some countries have ranges of barcode prefixes such as, 730 - 739; in such a case, a number from within that range will be considered as a valid output. Input: Netherlands Output:
870
Problem: Given the question: On a scale of 1-5 (with 1 being least favorable and 5 being most favorable), how would you rate this review? "Excellent" ++++++++++++++++++++++++++++++++ The answer is: 5 Problem: Given the question: On a scale of 1-5 (with 1 being least favorable and 5 being most favorable), how would you rate this review? "It's very nice app I like it ." ++++++++++++++++++++++++++++++++ The answer is: 5 Problem: Given the question: On a scale of 1-5 (with 1 being least favorable and 5 being most favorable), how would you rate this review? "Akhil Nice" ++++++++++++++++++++++++++++++++ The answer is:
5
Definition: In this task you will be given a list of numbers and you need to find the mean (average) of that list. The mean of a list can be found by summing every number in the list then dividing the result by the size of that list. The output should be rounded to 3 decimal places. Input: [132.008, -28.11, -90.573, 196.93, 26.971] Output:
47.445
In this task you're given two statements in Gujarati. You must judge whether the second sentence is the cause or effect of the first one. The sentences are separated by a newline character. Output either the word 'cause' or 'effect' . -------- Question: મહિલા બિસ્કીટને કૂતરાની ઉપર ઝૂલતી હતી. કૂતરો કૂદી ગયો. Answer: effect Question: નવું ચાલવા શીખતું બાળક ઘેલું બની ગયું. તેની માતાએ તેને નિદ્રા માટે નીચે મૂક્યો. Answer: effect Question: માણસની આંખમાં ચેપ લાગ્યો. તે આંધળો ગયો. Answer:
effect
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. Input: I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN 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_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK Output:
run around right twice and walk around left thrice
Q: In this task your given a passage in Catalan. you must ask a question in Catalan, that is relevant to the passage. A question that is constructed should be precise and based on factual information from the passage. A constructed question should be: (a) unambiguous (b) be directly answerable from the passage (c) have a unique answer (d) have an answer that is a continuous span of text from the passage. Try to avoid formulating questions that (a) can be answered without referring to the passage, or (b) use exactly the same words or questions given in the passage. Try to make the question fluent in the language used. You have to create exactly one question. Duran i Cañameres va fer estudis comparatius amb altres obres en els quals descriu la barreja que aprecia en l'obra de motius romànics i gòtics. Els arcs trilobats que presenta una de les cares rectangulars de l'arca i els laterals són similars als d'altres obres del segle xiii i al frontal d'altar dedicat a la mare de Déu que va pertànyer al monestir de Sant Cugat (actualment al Museu Civico d'Arte Antica de Torí.[8][9] A part d'aquest frontal, també hi ha aquest mateix tipus d'arcs i amb la mateixa datació que l'urna al frontal de l'església de Santa Perpètua de Mogoda i al frontal de l'església de Sant Cebrià de Cabanyes.[10] A:
Quina barreja aprecia en l'obra Duran i Cañameres?
Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)]. One example is below. Q: ['hey', 'everybody', 'ivan', 'from', 'weights', 'and', 'biases', 'here', 'in', 'this', 'video', "i'd"] A: ['CASE_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'CASE_DIFF', 'UNKNOWN_TYPE_DIFF', 'CASE_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_DIFF'] Rationale: This sentence is a good example since the input stream is a grammatically incorrect statement and the output labels correctly classify the words that were incorrect. Q: ['so', "you're", 'probably', 'feeling', 'pretty', 'comfortable', 'with', 'the', 'diagram', 'of', 'the', 'heart', 'but', 'let', 'me', 'just', 'go', 'ahead', 'and', 'label', 'a', 'few', 'things', 'just', 'to', 'make', 'sure', "we're", 'all', 'on', 'the', 'same', 'page', 'so', 'blood', 'flows', 'from', 'the', 'right', 'atrium', 'to', 'the', 'right', 'ventricle', 'and', 'then', 'goes', 'to', 'the', 'lungs', 'and', 'then', 'the', 'left', 'atrium', 'to', 'the', 'left', 'ventricle', 'so', "that's", 'usually', 'the', 'the', 'flow', 'of', 'blood', 'and', 'one', 'of', 'the', 'things', 'that', 'keeps', 'the', 'blood', 'flowing', 'in', 'the', 'right', 'direction', 'we', 'know', 'is', 'the', 'the', 'valves', 'and', 'two', 'of', 'the', 'valves', "I'm", 'actually', 'going', 'to', 'name', 'that', 'give', 'you'] A:
['CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF']
You will be given a definition of a task first, then some input of the task. In this task, you will be presented with a question having multiple possible answers in Vietnamese language. And you should choose a most suitable option out of "A", "B", "C", "D", and "E" based on your commonsense knowledge. Question: Thật là ngột ngạt nên cô quyết định hít thở không khí trong lành, kết quả là sao? Options: A cứu trợ B năng lượng C cảm thấy tốt hơn D thư giãn E Im lặng Output:
C
Definition: Sometimes users of dialogue systems ask vague questions/queries from the system. In this case, the system asks them a clarifying question to be able to answer it correctly. In this task, you are given a question/query in natural language and your task is to ask a good clarifying question to understand the given question/query more precisely. Input: I am looking for sources of used car parts. Output:
are you interested in a specific part
Instructions: You will be asked how to do a certain task. You should describe a physical process that does not lead to the asked outcome, yet it is closely related to it (i.e., it should use the words that are provided in the input). The physical process can be moving something, arranging something in a certain way, mixing things, shaking them, etc. To make sure that the generated process does not lead to the asked outcome, you can introduce objects or events unrelated to the context of the question e.g. 'cleaning the keyboard by making an elephant sit on them'; or you can create contradictory statements e.g. 'drying wet keyboards with running water'. In your responses, avoid typos and misspellings. Input: How do I get the wood I am working on to be smoother? Output:
Use some sandpaper to hit the wood.
Detailed 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. Problem:Love Is Like.... Solution:
love be like a long summer day in which i wish it'd stay that way now with whom do i share my love a heavenly angel from up above love be like the forever blowing breeze it swivel and swerve with such lovely ease like the autumn leave that blow how far will my love for you go love be like a white snowflake you'll never know which road it'll take lovely whiteness all around i know with you i'll never frown love be like a blooming spring flower it have that excellent love power it's warmth spread around you like the warm spring sun and this be how i know our love be a powerful one
You are given a sentence from a conversation between a human and a virtual assistant. Your task is to classify the sentence into one of the following five action categories - INFORM, INFORM_INTENT, OFFER, REQUEST, REQUEST_ALTS. If the sentence is about informing something, generate 'INFORM'. If it is about requesting something, generate 'REQUEST'. If the sentence mentions requesting an alternative option than the one provided, generate 'REQUEST_ALTS'. Similarly, generate 'OFFER' if the sentence is offering some information. If the sentence is about showing intent to do something, generate 'INFORM_INTENT'. [Q]: Will you find me a song? [A]: INFORM_INTENT [Q]: Some kind of Music event would be cool. [A]: INFORM [Q]: I am looking for an event to attend. Can you help me? [A]:
INFORM_INTENT
You are given first 5 messages from a series of message exchanges between 2 persons playing the game of Diplomacy which is an American strategic board game. You need to generate the next message. The message should be generated such that it fits the context seen so far. Avoid the text that is (i) tangent to the context, (ii) repeats the context. Q: ["Hi Germany! I'd love for us to start out on the right foot...let me know if you'd like to discuss the three B's (Burgundy, Belgium, and Britain) or anything else, for that matter 🙂", 'Yes, I’d be more than happy to discuss this', 'I haven’t spoken with England yet but I’m in favor of an equal split of Belgium and Holland between us. I’d like to open against Russia so if we can agree to dmz burgundy that will also free you up to focus on either England or Italy. What do you think?', 'When you say “split of bel and hol between us”, does “us” mean you and me? If so, then you’re suggesting exactly what I was going to suggest! That also goes for the bur dmz.\nI’ve also not heard anything from Britain yet but I’ll let you know if I do', 'It’s nice that we’re on the same wavelength'] A: I think so too **** Q: ["Hello there! What's your general plan for this game? My inclination when I play Austria is to piss off as few people as possible, so I don't plan on making any overtly aggressive moves this turn.", 'I suggest containment of Russia at the very least and perhaps his destruction', 'That certainly sounds just fine to me. I think Turkey and Austria can make for a very good alliance - you build a bunch of fleets, I build a bunch of armies, and we crush a bunch of dots.', 'Ok lets roll I’ll go north for the opening', 'If you want to contain Russia I am willing to support you into rum if you want to wait that’s ok too'] A: I'd love the support, thanks. **** Q: ['Hey Turkey! How are you doing? Looking forward to working with you this game!', 'You there? Would love to talk strategy at some point', "Hey Austria, yeah, I'm around", "Good to hear from you! How's your night?", "I'm kind of getting the grips on this game"] A:
No worries! Are you friend of admin? ****
Part 1. Definition In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the count of all the numerical elements in the given list. Return 0 if no numerical element in the list. Part 2. Example ['238', 'h', '92', 'U', '2799'] Answer: 3 Explanation: Here, the numbers in the input list are '238', '92' and '2799', hence their count is 3. Part 3. Exercise ['E', '2973', 'O', 'F', '2939', 'Z', '8307', 'm', 'Y', '5035', '4607', '6177', 'i', '8017', 'C', '8537', '4373', '2331'] Answer:
10
Instructions: In this task, you are provided with an article of the legal acts. Your task is to classify it into three categories (Regulation, Decision and Directive) based on its content: 1) Regulation is a binding legislative act that must be applied in its entirety on a set date across all the member states (European Union countries). 2) Decision is binding on those to whom it is addressed (e.g. an European Union country or an individual company) and is directly applicable. 3) Directive is a legislative act that sets out a goal that all must achieve. However, it is up to the individual countries to devise their own laws on how to reach these goals. Input: The text of Article 6 of Regulation No 282/67/EEC shall be supplemented by the following paragraph 4:'4. The intervention agency shall indicate a delivery place other than the centre indicated by the holder of the seeds if that centre does not, at the time of the transaction, offer sufficient storage capacity for the product in question or does not provide sufficient guarantee of good storage conditions for the products under intervention.The place of delivery indicated by the intervention agency shall be the place where, among such places as fulfil the requirements of storage capacity and good storage conditions, the total expenditure resulting from storage costs and the change in transport costs is the most favourable.' The following Article 8a shall be added to Regulation No 282/67/EEC:'Article 8aWhile awaiting Community provisions on this matter, Member States shall take all suitable measures to ensure that the seeds which have been the subject of intervention are kept in good condition.They shall inform the Committee of provisions adopted in pursuance of the preceding paragraph.' This Regulation shall enter into force on the third day following its publication in the Official Journal of the European Communities. (1)OJ No 172, 30.9.1966, p. 3025/66. (2)OJ No L 314, 31.12.1968, p. 1. (3)OJ No 151, 13.7.1967, p. 1. (4)OJ No L 186, 30.7.1969, p. 7.This Regulation shall be binding in its entirety and directly applicable in all Member States. Output:
Regulation
TASK DEFINITION: Indicate with `Yes` if the given question involves the provided reasoning `Category`. Indicate with `No`, otherwise. We define five categories of temporal reasoning. First: "event duration" which is defined as the understanding of how long events last. For example, "brushing teeth", usually takes few minutes. Second: "transient v. stationary" events. This category is based on the understanding of whether an event will change over time or not. For example, the sentence "he was born in the U.S." contains a stationary event since it will last forever; however, "he is hungry" contains a transient event since it will remain true for a short period of time. Third: "event ordering" which is the understanding of how events are usually ordered in nature. For example, "earning money" usually comes before "spending money". The fourth one is "absolute timepoint". This category deals with the understanding of when events usually happen. For example, "going to school" usually happens during the day (not at 2 A.M). The last category is "frequency" which refers to how often an event is likely to be repeated. For example, "taking showers" typically occurs ~5 times a week, "going to Saturday market" usually happens every few weeks/months, etc. PROBLEM: Sentence: Grants of tax-free land over the years had been made to Buddhist temples and members of the court aristocracy. Question: When were the grants introduced? Category: Absolute Timepoint. SOLUTION: Yes. PROBLEM: Sentence: Boston Center TMU [Traffic Management Unit], we have a problem here. Question: Is the problem still ongoing? Category: Transient v. Stationary. SOLUTION: Yes. PROBLEM: Sentence: Wallace lives in Athens, W. Va., with her husband Rob, 37, and her daughters Rachel, 11, and Claire, 5. Question: How long has Wallace lived in Athens? Category: Event Duration. SOLUTION:
Yes.
Detailed Instructions: Given an input word generate a word that rhymes exactly with the input word. If not rhyme is found return "No" Problem:wife Solution:
knife
The input is a tweet which can be Hate Speech or Offensive. Given such a tweet, output a phrase from the tweet that makes it hate speech or offensive. The output should contain only one such phrase. The output has to be from within the tweet itself. Do not generate words or phrases not present in the tweet. well i apologise for any ozeez that might have forgotten that we can take the piss but go too hard and somethings amiss i do find that seppos do not understand aussie british humour and can take things personally everyones a liberal snowflake to an aussie and then they imported muzzies here damit
muzzies
Teacher:In this task, you are given a sentence which contains a motion and your task is to identify the physical entities involved in the motion. The input sentence can have more than one entity and also there is at least one entity that takes part in physical motion. There are two types of entities which are animate (beings that are alive) and inanimate entities (beings that are not alive). Teacher: Now, understand the problem? Solve this instance: Walderhurst went to him. Student:
Walderhurst
Instructions: Given the sentence, generate "yes, and" response. "Yes, and" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated ("Yes") and then expand on that line of thought or context ("and..."). 1 In short, a "Yes, and" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a "Yes, and" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'. Input: Are you under a bit of a time crunch? Output:
I am, I've got a big meeting at nine.
Q: Given a premise and a hypothesis, determine if the hypothesis (second sentence) can be concluded from the premise and assigning it a label among entailment, neutral, or contradiction. Entailment means thats the hypothesis makes sense/follows after the premise. Neutral means that the hypothesis does not follow the premise but also does not contradict the premise. Contradiction means that the hypothesis clearly contradicts the premise. People are conversing at a dining table under a canopy. <sep> People are talking underneath a covering. A:
entailment
You will be given a topic and an argument. Decide the argument's stance towards that topic. The argument's stance is in favor or against the topic. If the argument supports that topic, answer with "in favor"; otherwise, if the argument opposes the topic, answer with "against". topic: Underground nuclear waste storage argument: Underground storage important to safety across borders.
in favor
In this task, you need to indicate the presence of temporal reasoning in the provided question. Questions that involve temporal reasoning/understanding contain one of the following five temporal phenomena: First: "event duration", is defined as the understanding of how long events last (e.g.,"brushing teeth" usually takes a few minutes). Second: "transient v. stationary" events, which are based on the understanding of whether an event will change over time or not (e.g., "being born in the U.S." is a stationary event since it will last forever; "being hungry" is a transient event since it lasts for a short period of time). Third: "event ordering" is the understanding of how events are usually ordered (e.g., "earning money" usually comes before "spending money"). Fourth: "absolute timepoint" of events which is the understanding of when events usually happen (e.g., "going to school" usually happens during the day, not at 2 A.M). The last category is "frequency" of events, which refers to how often events are repeated (e.g., "taking showers" typically occurs ~5 times a week, "going to Saturday market" usually happens every few weeks/months, etc.). Indicate with `Yes` if the question involves temporal reasoning. Indicate with `No`, otherwise. One example is below. Q: Sentence: Jack played basketball after school, after which he was very tired. Question: How long did Jack play basketball? A: Yes. Rationale: The question asks about the duration of an event; therefore it's a temporal question. Q: Sentence: Finley only realizes with hindsight that his misdeeds far surpass those of Violet . Question: How long did it take Finley to realize? A:
Yes.
Given a sentence in the Japanese and Filipino language. Your task is check if the Filipino sentence is translation of Japanese. if the translation is correct than generate label "Yes", otherwise generate label "No". Q: Japanese: 適例を挙げると、この議案が実際通過するならば、スウェーデンはアフリカの小国への財政援助を減らすとその後脅迫した。 Filipino: Ang pagdiriwang ng araw ng komunidad ay binuo ng mga kasali sa Operasyon NANOOK 2008. A:
No
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". [Q]: Tweet: A 20-year-old female has become the first swine flu fatality in San Diego County. (via @SanDiego6) - dang, only 20yo... Question: is it a positive tweet? [A]: no [Q]: Tweet: Ugh...I waited way too long to eat dinner and now my tummy hurts Question: is it a positive tweet? [A]: no [Q]: Tweet: @jconley21 Hey Sweetie!!! Bob is in my prayers!!! I know being who you are it is so hard on you Question: is it a negative tweet? [A]:
yes
Instructions: In this task you are expected to write an SQL query that will return the data asked for in the question. 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. Input: What is the average bike availablility for stations not in Palo Alto? Output:
SELECT avg(bikes_available) FROM status WHERE station_id NOT IN (SELECT id FROM station WHERE city = "Palo Alto")
You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Portugese. [EX Q]: היא בסביבות 770 גרם פחמן. [EX A]: Cerca de 770 gramas de carbono. [EX Q]: היינו רוצים לדעת מה זה. [EX A]: Gostaríamos de saber o quê. [EX Q]: ידידו הטוב ביותר של האדם במאבק נגד המלריה. [EX A]:
O melhor amigo do homem na luta contra a malária.
Detailed Instructions: Classify the given comment into 'Hope Speech' or 'Not Hope Speech'. A hope speech is defined as content that is encouraging, positive or supportive contents and talks about equality, diversity or inclusion Problem:All Lives Matter - especially now. Solution:
Hope Speech
Teacher:You will be given a passage with an enumerated set of facts, a question of form 'Where is <person_name>?', and its answer. The task is to identify a supporting fact that is necessary to answer the question. The output would be the corresponding fact number. Teacher: Now, understand the problem? Solve this instance: Passage: Fact 1- Daniel went to the kitchen. Fact 2- Mary travelled to the hallway. Fact 3- Daniel went back to the garden. Fact 4- Mary went back to the bathroom. Fact 5- Sandra moved to the hallway. Fact 6- John moved to the garden. Question: Where is Daniel? Answer: garden Student:
Fact 3
Instructions: Given a sentence in the Central Khmer, provide an equivalent translation in Japanese that retains the same meaning through the translation. In translation, keep numbers as it is. Input: បប់ ប្រាត់ថុន តម្រួតខេត្តអុតតាវ៉ាបានហៅមនុស្សដែលគេចវេះមិនអើពើពីការព្រមានទាំងនេះថា "ភ្លីភ្លើ។" Output:
オタワ郡保安官のボブ・ブラットン氏は警告を無視した人を「大ばかだ」といった。
Question: You are considering whether to buy a product. You look at the reviews. Would the following review decrease or increase the chances of you buying the product? Review title: Ok to be basic but not that way Product review: isnt a good book, cause even the basic is out of this book, ahrd to get it, the exemples are no clear and you get tired of it in few minutes, what the science use to call; lazy brain. but if you want try it dont blame me later , cause i told you so Answer: decrease Question: You are considering whether to buy a product. You look at the reviews. Would the following review decrease or increase the chances of you buying the product? Review title: Best Launch title Ever!! Product review: This game is totally awesome. I mean, or course, it takes a little bit to get use to playing a FPS on the console, but once you get through that, it rules. The story rocks, the graphics rock, there's absolutely nothing wrong with it except that there aren't any bots for multiplayer. That's only a tiny loss, however, since the single player game is awesome anyway. Answer: increase Question: You are considering whether to buy a product. You look at the reviews. Would the following review decrease or increase the chances of you buying the product? Review title: twin towers Product review: I ordered this book for my 6 1/2 year old son who is facinated with the Towers. Nice pictures of the WTC from its early days and building, and tastefully done pictures of its sad destruction. The pictures are taken from all over the New York Metropolitan area emphasizing their past domination of New York's signature sky line. Very little prose other than picture identification, and my son can spend hours pouring over the pictures. I would have appreciated a few more close up shots and interior picture and views, but all in all, a nicely done memoir. Answer:
increase
Indicate if the following Polish tweet contains cyber-bullying content with 'Yes'; otherwise, respond with 'No'. Example Input: Tweet: @anonymized_account Kariera Vidala - 91 goli, 5 czerwonych kartek. Pytania? 😉 , Question: Does the tweet contain cyberbullying (harmful) content? Example Output: No Example Input: Tweet: RT @anonymized_account @anonymized_account @anonymized_account @anonymized_account Bicie i gwałcenie żony przez radnego PiS nazywasz nadużyciem?\nTo zbrodnia Panie Poręba. , Question: Is the tweet free of any cyberbullying (harmful) content? Example Output: Yes Example Input: Tweet: @anonymized_account @anonymized_account Kurde! Ja też się wzruszyłem😁😁😁 , Question: Does the tweet contain cyberbullying (harmful) content? Example Output:
No
Given the task definition, example input & output, solve the new input case. The input is taken from a negotiation between two participants who take the role of campsite neighbors and negotiate for Food, Water, and Firewood packages, based on their individual preferences and requirements. Given an utterance and recent dialogue context containing past 3 utterances (wherever available), output Yes if the utterance contains the elicit-pref strategy, otherwise output No. elicit-pref is a cooperative negotiation strategy. It is used to discover the preference order of the opponent in the negotiation. Example: Context: 'What do you think if in the camp we get together and have a meeting between your family and mine? We can have a small party to get to know each other better.' 'Sounds great!' 'Ok, my proposal is to give you all the firewood you need, on the condition that you give me all the water I need. And regarding food we can negotiate.' Utterance: 'That sounds good. What do you propose on the food?' Output: No The primary utterance does not try to elicit information on the preference order of the participant. So this is correct. New input case for you: Context: 'It's good, thank you 🙂 Which package is the most important for you to have on your trip do you think?' 'That would be firewood. Even though is really hot there, it gets cold at night. How's the weather for you? 🙂' 'Ah yes, you'll definitely need some extra wood then! It's also pretty cold here, especially during the night. But I would definitely be willing to let you take 2 firewood in exchange for 3 food. We have a lot of people going and will be out in the middle of nowhere.' Utterance: 'We can definitely work something out. I'll be sure it'll benefit you more than me. 🙂' Output:
No
Problem: Process: - Bread is exposed to the elements - Bread absorbs water from the air - Bread absorbs warmth from the air - Dust particles with mold spores fall on bread - Mold spores start to consume the bread for energy - Mold colonies grow until they are visible. Perturbation hypothesis: suppose the bread is cleaned off happens, how will it affect an increase in dust particles on the bread. Does the supposed perturbation have an effect (direct or indirect) on the process? A: yes Problem: Process: - A person eats food - The person's blood sugar level rises - The pancreas receives a signal to release insulin - Insulin is released into the bloodstream - Insulin signals cells to absorb sugar - The cells absorb sugar from the bloodstream - The cells use the sugar as energy. Perturbation hypothesis: suppose having genetic illness happens, how will it affect LESS use of insulin in the body. Does the supposed perturbation have an effect (direct or indirect) on the process? A: yes Problem: Process: - Warm water floats up from the ocean - A pocket of low pressure air is created near the surface of the ocean - Warm air from outside areas pushes into the low pressure area - The warm air keeps rising and forms clouds - The wind is getting fed moisture that evaporates from the ocean - This moisture causes the swirling air and clouds to grow bigger - As it gets bigger the wind rotates faster. Perturbation hypothesis: suppose more sunny days happens, how will it affect LESS POWERFUL hurricanes. Does the supposed perturbation have an effect (direct or indirect) on the process? A: no Problem: Process: - The bird picks a tree - The bird collects twigs and other refuse - The bird makes a flat base with twigs - The bird makes sides with twigs and other things - The bird adds softer material to the inside - The nest is done. Perturbation hypothesis: suppose there are fewer trees happens, how will it affect there will be more trees. Does the supposed perturbation have an effect (direct or indirect) on the process? A:
yes
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. Input: 23, 26, ['7489', 'c', 'X', 'b', 'c', 'T', '8427', '3953', '7737', '1485', '7391', '6549', 'S', '559', '789', 'y', '4081', 'D', '1259', 'W', '1835', '595', 'N', '8709', '7359', 'l', 'k'] Output:
l95379078N
In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the count of all the numerical elements in the given list. Return 0 if no numerical element in the list. One example: ['238', 'h', '92', 'U', '2799'] Solution is here: 3 Explanation: Here, the numbers in the input list are '238', '92' and '2799', hence their count is 3. Now, solve this: ['a', '4109', 'H', '3413', '129', '2887', 'C', 'Q', '9685', '5891', 'e', '3485', 'L', '9899', '5151', 'b', 'p', 'N', '6723', '4221', 's', 'Y', 'o', 'r', 'v', '5615', 'g', 'y', 'n', '7837', 'T', 'O', '2751', 'I', 'U'] Solution:
14
Detailed Instructions: 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". Q: What is on my calendar early next week? A:
user
In this task, you are given a tweet in English. You are expected to classify the post into two classes: sarcastic or non-sarcastic. A sarcastic sentence is one that refers to the use of words that mean the opposite of what you really want to say, especially in order to insult someone, or to show irritation, or just to be funny. Ex Input: I t seems the only time I can stay awake now it's at 4:30 in the morning . No need to sleep anymore . Don't worry . I'm fine . #FML Ex Output: sarcastic Ex Input: Doesn't everyone love getting allergy shots once a week ? #sarcasm Ex Output: sarcastic Ex Input: If you're going into highschool and cant do at least 4 pirouettes you obviously go to a fantastic studio #sarcasm Ex Output:
sarcastic
instruction: Two analogies that relate actions to the tools used to perform the action is given in the form "A : B. C : ?". "A : B" relates action A to tool B. Your task is to replace the question mark (?) with the appropriate tool for the given action C, following the "A : B" relation. question: wash : detergent. toast : ? answer: toaster question: cut : scissors. mop : ? answer: mop question: hit : hammer. cook : ? answer:
pan
Detailed Instructions: This task is to find the number of 'For' loops present in the given cpp program. Problem://********************************* //* file?1.cpp //* description: ???? //* author: ?? 1200012858 //* date: 2012-12-1 //********************************* int decompose(int x, int y); int main () { int n, m; cin >> n; for (int j = 1; j <= n; j++) { cin >> m; cout << decompose(m, 2) << endl; } return 0; } int decompose(int x, int y) { int sum = 1,b; b = (int)sqrt(x); if (x == 1) return 0; for (int i = y; i <= b; i++) { if (x % i == 0) { sum = sum + decompose(x / i, i); } } return sum; } Solution:
2
Detailed Instructions: Given two entities as input, classify as "yes" if second entity is the part of the first entity. Otherwise classify them as "no". These are entities of meronym In linguistics, meronymy is a semantic relation between a meronym denoting a part and a holonym denoting a whole. In simpler terms, a meronym (i.e., second entity) is in a part-of relationship with its holonym (i.e., first entity). Problem:Entity 1: elver Entity 2: body Solution:
yes
Instructions: Given a sentence in Italian, generate a new Italian 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. Input: Nell'ufficio cinema, è possibile spegnere la musica delle cellule. Output:
Nel cinema, puoi spegnere il cellulare.
You are supposed to identify the category of a high-school level math question. There are five possible categories (1) algebra (2) arithmetic (3) measurement (4) numbers, and (5) probability. Use the following guidelines: (1) 'algebra' questions will typically contain letter variables and will ask you to find the value of a variable (2) 'arithmetic' questions will ask the sum, difference, multiplication, division, power, square root or value of expressions involving brackets (3) 'measurement' questions are questions that ask to convert a quantity from some unit to some other unit (4) 'numbers' questions will be about bases, remainders, divisors, GCD, LCM etc. (5) 'probability' questions will ask about the probability of the occurrence of something. A question must belong to only one category. One example: Suppose -d - 13 = -n - 0, 0 = 2*d + 2. Solve 2*x = -10 + n for x. Solution is here: algebra Explanation: This is a system of three linear equations, clearly an 'algebra' question. Standard methods of solving linear equations can be used to obtain the solution. Now, solve this: Solve 6*m = 7*m - 4*o - 8, -m + 4 = -2*o for m. Solution:
algebra
Q: The input is taken from a negotiation between two participants who take the role of campsite neighbors and negotiate for Food, Water, and Firewood packages, based on their individual preferences and requirements. Given an utterance and recent dialogue context containing past 3 utterances (wherever available), output Yes if the utterance contains the uv-part strategy, otherwise output No. uv-part is a selfish negotiation strategy. It is used to undermine the requirements of the opponent. For instance, suggesting that the opponent would not need more firewood since they already have the basic supplies or a suggestion that there might be a store near the campsite where the opponent can get the supplies instead. Context: 'Hi! I'm super excited to go camping with my family as a great way to vacation due to Covid19. My kid is so restless from being cooped up in the house all the time. Are you planning on going camping too?' 'I am! It is the perfect way to get away and still manage to social distance! I am worried about having enough water though, are you short on any supplies?' Utterance: 'I think I'm good. I'm not 100% sure. My husband likes to do adventures on the fly. He got these water filter straw thingies from Amazon and said that if we run out of the water I packed, that we can drink the water in the lake but I don't really trust the straws.' A:
No
You will be given a definition of a task first, then some input of the task. In this task, you are given two sets, and you need to count the number of elements at the union of two given sets. A Set is shown by two curly braces and comma-separated numbers inside, like {1, 2, 3}. Union of two given sets is the smallest set which contains all the elements of both the sets. To find the union of two given sets, A and B is a set that consists of all the elements of A and all the elements of B such that no element is repeated. Set1: '{2, 6, 7, 11, 20}', Set2: '{2, 3, 5, 9, 17, 18, 19}'. How many elements are there in the union of Set1 and Set2 ? Output:
11
The provided file includes inquiries about restaurants, and we ask you to translate those to the Polish language. Please bear in mind the following guidlines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are *NOT* looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 *SHOULD NOT* be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for special placeholders. Please do the same in your translations. what 's the address of the " mcdonald 's " on " parker road " ? jaki jest adres "mcdonald 's" na "parker road"? are there any " indian " restaurants near me ? czy są jakieś " indian " restauracje w pobliżu? how many reviews have been posted for " old town doughnuts " ?
ile recenzji zostało napisanych dla "old town doughnuts"?
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task. In this task, you are given a context sentence containing a blank (_). You are expected to fill the blank with one word to make the sentence convey a cultural stereotype. A stereotype is an over-generalized belief about a particular group of people. Your answer must not contain more than one word. Context: Every commander tends to be _. Solution: controlling Why? Commanders are controlling is an existing and valid stereotype. New input: Context: The country of Yemen was seen as being very _. Solution:
violent
You are given a sentence in Persian. Your job is to translate the Farsi sentence into Galician. -------- Question: و فرد منتظر دوست دخترش است. Answer: E estamos agardando pola nosa moza. Question: خوب ، دوباره به آن تصاویر نگاه کنید. Answer: Miren de novo esas imaxes brillantes. Question: و بنابراین در این مکان ، با همان آسیب ‌ پذیریها ، همان نقاط قوت ، همان ترسها ، همان امیدها ، امیدوارم با هم با شادمانی کار کنیم. Answer:
E así neste lugar coas mesmas vulnerabilidades, idénticas fortalezas, medos e esperanzas, agardo que poidamos traballar xuntos con alegría.