prompt
stringlengths 47
13.7k
| response
stringlengths 0
3.54k
|
|---|---|
Given the task definition and input, reply with output. In this task, you will be given sentences in which your task is to recognize the name of the drug or medicine. Drugs are substances that change a person's mental or physical state. They can affect how your brain works, how you feel and behave, your understanding, and your senses. Although there might be several correct answers, you need to write one of them.
Following are two clinical case reports demonstrating profound cerebral edema associated with implantation of Gliadel wafers.
| Gliadel |
You will be given a definition of a task first, then some input of the task.
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
I’m lesbian and I’m so glad that I didn’t have to go through this. I’m sorry you had to go through this. I mean technically I’m only out to my friends and my Mam and brother I’m kinda scared to come out to the rest of my family
Output: | Hope Speech |
Detailed Instructions: In this task, you are given a country name, and you need to return the year in which the country became independent. Independence is a nation's independence or statehood, usually after ceasing to be a group or part of another nation or state, or more rarely after the end of military occupation.
Q: United Arab Emirates
A: | 1971 |
You are given an original reference as well as a system generated reference. Your task is to judge the naturaleness of the system generated reference. If the utterance could have been produced by a native speaker output 1, else output 0.
Example Input: System Reference: the phone number for canto do brasil restaurant is 4156268727, and the postcode is 94102.
Original Reference: the phone number for canto do brasil restaurant is 4156268727, its postcode is 94102.
Example Output: 1
Example Input: System Reference: may i ask near where?
Original Reference: what area of the city are you looking for.
Example Output: 0
Example Input: System Reference: there is a chinese restaurant on x called x.
Original Reference: x is a chinese restaurant in the x area.
Example Output: | 0
|
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.
Q: [7, 6, 0, 7, 2]
A: | [6, 0, 2] |
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.
Q: Le persone scelgono di vedere il contrario.
A: La gente va a vedere la palla.
****
Q: Lavoreresti in coma perche' vuoi la tortura.
A: Mangeresti in un cilindro perche' vuoi l'ossigeno.
****
Q: Se si vuole presentare un esame allora si dovrebbe andare a scuola.
A: | Se vuoi fare un esame allora dovresti andare a scuola.
****
|
Given the task definition, example input & output, solve the new input case.
In this task, you are given a country name and you need to return the region of the world map that the country is located in. The possible regions that are considered valid answers are: Caribbean, Southern Europe, Eastern Europe, Western Europe, South America, North America, Central America, Antarctica, Australia and New Zealand, Central Africa, Northern Africa, Eastern Africa, Western Africa, Southern Africa, Eastern Asia, Southern and Central Asia, Southeast Asia, Middle East, Melanesia, Polynesia, British Isles, Micronesia, Nordic Countries, Baltic Countries.
Example: Angola
Output: Central Africa
Angola is located in the Central Africa region of the world map.
New input case for you: Malaysia
Output: | Southeast Asia |
In this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command:
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.
Q: select the rows whose location attendance record fuzzily matches to pepsi center . select the row whose location attendance record of these rows is maximum . the date record of this row is november 1 .
A: | eq { hop { argmax { filter_eq { all_rows ; location attendance ; pepsi center } ; location attendance } ; date } ; november 1 } |
Detailed Instructions: In this task, you need to answer 'Yes' if the given word is the longest word (in terms of number of letters) in the given sentence, else answer 'No'. Note that there could be multiple longest words in a sentence as they can have the same length that is the largest across all words in that sentence.
Q: Sentence: 'the beach is decorated with very colorful canopies'. Is 'colorful' the longest word in the sentence?
A: | No |
TASK DEFINITION: Given a negotiation between two participants, answer 'Yes' if both participants agree to the deal, otherwise answer 'No'.
PROBLEM: THEM: hi, can i have 2 books and 2 hats? YOU: i will give you all of the hats, but i will need the ball and two books. THEM: no, i`ll take the 2 books and 2 hats. it`s the best i can do YOU: can't do that. how about i take the ball and one book, leaving you with four hats and one book? THEM: no, i can`t do that YOU: then i guess we're not going to agree on a deal, because i would need at least one book and the ball. THEM: no deal YOU: no deal THEM: no deal YOU: no deal.
SOLUTION: No
PROBLEM: THEM: i will take hat, 1 book, and 1 basketball, you can have 2 books YOU: i need a hat and a ball... you can have all the books THEM: no can do i need the hat and 2 books YOU: i need the hat as well...... books are zero value on my end THEM: i can't give up the hat. i will take the hat you can have the rest YOU: again, i get zero value on the books THEM: well i can't give up the hat so don't have anything else to offer YOU: ok... click on the no deal button and we can go to the next deal THEM: have to wait for it to turn green YOU: ok.
SOLUTION: No
PROBLEM: THEM: i would like ball and 3 hats YOU: no thanks, i can give you 3 hats, final offer THEM: i want either ball or book plus 3 hats YOU: nope THEM: i guess we both get nothing YOU: i guess so THEM: bye YOU: bye, you have to click on no deal was agreed.
SOLUTION: | No
|
Process: - Oil is gathered through mining operations - The oil is transported to stores - Oil is purchased by homeowners - Oil is placed into a stove in the house - The oil is lit on fire, and burns for a long time - The warm air off of the oil travels through the house - Perturbation hypothesis: suppose more oil lit on fire happens, how will it affect less heat for the house. Does the supposed perturbation have an effect (direct or indirect) on the process?
| yes |
TASK DEFINITION: Based on the given context, craft a common-sense question, especially those that are LONG, INTERESTING, and COMPLEX. The goal is to write questions that are easy for humans and hard for AI machines! To create such questions, here are some suggestions: A. What may (or may not) be the plausible reason for an event? B. What may (or may not) happen before (or after, or during) an event? C. What may (or may not) be a plausible fact about someone (or something)? D. What may (or may not) happen if an event happens (or did not happen)? You can also create other types of questions. DO NOT make your question answerable without looking at the context, or question of which the correct answer can be directly extracted from the context. DO NOT ask a question that requires very specialized knowledge that is not common sense. DO NOT ask too simple or too short questions. Your question must be related to the context and answerable with common sense. Try to add more variations and complexity to the questions.
PROBLEM: Context: I ran out into the hallway , and joined a crowd going down the stairs . At the third floor , someone at the front of the crowd started saying we could n't get out . I shouted that we should at least go down and try : it 's better than standing in the stairwell . At the second floor , a woman was holding the stairwell door open , gesturing for us to follow . The student lounge was jam - packed , the wide - screen tv was turned on to CNN .
SOLUTION: Why were these students locked in ?
PROBLEM: Context: I ' m always at war with my weight because I ' m not eating right , I ' m stressed over stupid things sometimes . Basically I do a good job of beating myself up and letting things bother me that I really should n't . Now it 's hard to change all that but I think I can . I need to just buckle down and be happy with who I am and take all my insecurities and flaws and realize they are what make me a Melissa and I have to deal with it .
SOLUTION: How would one describe a trait of the narrator 's personality ?
PROBLEM: Context: Fun , his mugger had a buddy . He hoped they 'd enjoy time in a cell together . Hmm , let 's test out how well they liked one another . He started shooting webs and all too soon he had them tied together and hung them up on a lantern post .
SOLUTION: | What superhero may be described ?
|
Detailed Instructions: 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.
Problem:Context: 'Hello!' 'Hello! Yay, we get to camp!' 'Heck yes! I am excited. How about you?'
Utterance: 'I can't wait 🙂 Let's talk about these supplies. I've got hungry mouths to feed, Can I take the food and you can have half the firewood and all the water?'
Solution: | No |
In this task, you are given two lists A,B. Find the longest common subsequence in the lists A and B.
Example Input: [1699, 5363, 'U', 3351, 'K', 1771, 8981, 'y', 4317, 'P', 'H', 'f', 'j', '7169', '129', 'Z', 'K', 'r', 'o', 'v', '1713', 'g', 'A', 'h', 'e', '421', 'a', 'b'], [1477, 'o', 'h', 4413, 'Y', 'V', 4539, 't', 'S', 3527, 9183, 9541, '7169', '129', 'Z', 'K', 'r', 'o', 'v', '1713', 'g', 'A', 'h', 'e', '421', 'j', 'V', 8579, 3395, 'l', 'X', 'l', 'm', 4239]
Example Output: 7169, 129, Z, K, r, o, v, 1713, g, A, h, e, 421
Example Input: ['y', 'T', 'W', 'v', 3541, 5233, 'w', 8885, 'o', 9621, 'e', 457, 'z', 'D', 5225, 'm', 'U', '8669', '4471', '3119', 'Y', '1937', '1161', 't', 'o', 'm', '6349', 'f', 'x', 's', 'L', 'E', '7395', '7035', 'p', '9607', 'a', '7951', 'A', 5057, 'S', 983, 8121, 'Y', 'I', 6217, 987, 'U', 2147, 'n'], ['R', 8175, 6613, 8767, 7071, 6707, 'V', 6635, 'n', 'Z', 8325, 6011, 8089, 2053, 'm', 'U', '8669', '4471', '3119', 'Y', '1937', '1161', 't', 'o', 'm', '6349', 'f', 'x', 's', 'L', 'E', '7395', '7035', 'p', '9607', 'a', '7951', 'E', 2901, 4455, 739, 'M', 'd', 1735, 'i']
Example Output: m, U, 8669, 4471, 3119, Y, 1937, 1161, t, o, m, 6349, f, x, s, L, E, 7395, 7035, p, 9607, a, 7951
Example Input: [9475, 'k', 'r', 9597, 5761, 'B', 'v', '543', 'M', '9807', '7001', '7261', 'r', 'm', '5447', 'r', '2223', 'U', '3235', '9375', '1293', '375', 'H', '6719', 'n', 'V', 'l', 'b', 5715, 'x', 6569, 'N', 9421, 'D', 'Q', 'i', 161, 'F', 9073, 2635, 'A', 5371, 6989, 9287, 5405, 'T', 'V', 1875], [2255, 6857, 5433, 'z', 3491, 6883, 's', 'P', 'v', '543', 'M', '9807', '7001', '7261', 'r', 'm', '5447', 'r', '2223', 'U', '3235', '9375', '1293', '375', 'H', '6719', 'n', 'V', 'l', 'S', 'j', 9143, 'q', 3049, 3153, 'z', 167, 5151, 3315, 9045, 'R', 6267, 'k', 'w', 2869, 8389, 9513, 4293]
Example Output: | v, 543, M, 9807, 7001, 7261, r, m, 5447, r, 2223, U, 3235, 9375, 1293, 375, H, 6719, n, V, l
|
Detailed Instructions: You're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from "sympathetic" to "stern"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them.
Problem:Context Word: tire.
Question: PersonX asked PersonY to pump up their tire and change the oil because _ didn't know how to.
Answer: PersonX
Solution: | PersonX asked PersonY to pump up their tire and change the oil because _ was a car mechanic. |
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.
Ex Input:
Keep cutting board in place.
Ex Output:
Place damp tissue paper under board.
Ex Input:
Learn to identify different bird species.
Ex Output:
Get a book of birds in your area and sit by your living room window. Watch the birds and compare to the pictures in your book. Holler at them and try to learn their whistles. Do this often and you will soon become an expert.
Ex Input:
How to cut fingernails with a nail clipper
Ex Output:
| Set the clippers to the "ready" position by rotating one of the small metal bars, if necessary. Put your fingernail in between the 2 blades. Pull the ends of the clippers apart in order to make the blades come into contact with each other, which will cut the fingernail.
|
In this task you will be given an arithmetic operation and you have to find its answer. The operators '+' and '-' have been replaced with new symbols. Specifically, '+' has been replaced with the symbol '@' and '-' with the symbol '#'. You need to perform the operations in the given equation return the answer
[Q]: 9682 @ 9507 # 7565 # 4252
[A]: 7372
[Q]: 9645 @ 911 @ 6748 # 3005 # 3625 # 87 @ 3003 # 5587 # 1382
[A]: 6621
[Q]: 5405 # 8803 # 8147 # 919
[A]: | -12464
|
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 Vaults], eatType[pub], priceRange[less than £20], customer rating[low], near[Café Adriatic]
A: The Vaults is a low rated pub located near Café Adriatic. It has a price range under £20.
****
Q: name[Fitzbillies], eatType[coffee shop], food[Indian], priceRange[high], customer rating[average], area[riverside], familyFriendly[no]
A: Fitzbillies is a coffee shop. It offers Indian food. It is in the high price range. It has a average customer rating. It is in the riverside area. It is not a children friendly restaurant.
****
Q: name[The Dumpling Tree], eatType[restaurant], food[French], priceRange[moderate]
A: | The Dumpling Tree restaurant specializes in French food with moderate prices.
****
|
Q: We would like you to assess the QUALITY of each of the following argument (discussing Gay Marriage) 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 gay marriage. An invalid argument is a phrase that cannot be interpreted as an argument or not on the topic of gay marriage.
Unlike many conservatives who, for example, are trying to pretend that judges don't have the right to rule on matters of law.
A: | Invalid |
Given the task definition and input, reply with output. Adverse drug reactions are appreciably harmful or unpleasant reactions resulting from an intervention related to the use of medical products, which predicts hazard from future administration and warrants prevention or specific treatment, or alteration of the dosage regimen, or withdrawal of the product. Given medical case reports extracted from MEDLINE, the task is to classify whether the case report mentions the presence of any adverse drug reaction. Classify your answers into non-adverse drug event and adverse drug event.
Amphotericin B nephrotoxicity in humans decreased by salt repletion.
| adverse drug event |
Given the task definition and input, reply with output. In this task you will be given a list of integers. You should round each integer to the nearest tens place. That means you should round the number to the nearest multiple of 10.
[-629, 513]
| [-630, 510] |
Given a part of privacy policy text, identify the type of personal information which is collected, used, tracked or retained. The type of information should be present inside the given policy text, answer as 'Not Specified' otherwise
Input: Consider Input: A named third party does receive your IP address or device IDs for analytics or research. The data is aggregated or anonymized.
Output: IP address and device IDs
Input: Consider Input: An unnamed third party does not receive your unspecified personal information for marketing purposes. You can opt in for data collection.
Output: Generic personal information
Input: Consider Input: A named third party does see your activities on the website or app for targeted advertising.
| Output: User online activities
|
Given the task definition and input, reply with output. 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.
[-14.472 17.597 77.078 -1.511 -68.923 -89.762]
| -89.762 |
In this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.
One example: twotwoonesixzeronine
Solution is here: 221609
Explanation: The string is properly converted into a number based on the spelling of each digit. The string started with 'twotwo' therefore the number also started with '22'. This is a good example.
Now, solve this: threesixeightsixfive
Solution: | 36865 |
Problem: Generate a 1-star review (1 being lowest and 5 being highest) about an app with package com.zegoggles.smssync.
A: Don't work It only backs up out going messages and no incoming messages
Problem: Generate a 2-star review (1 being lowest and 5 being highest) about an app with package com.totsp.crossword.shortyz.
A: It's ok The best one I have found so far. I hate the fact that it records letters I mistype as """"""""""""""""hinted""""""""""""""""... I'm using a touch screen. If it wasn't for autocorrect no one would be able to read this. I'd give 5 stars if they removed the hinted thing.""
Problem: Generate a 1-star review (1 being lowest and 5 being highest) about an app with package com.google.android.gms.
A: It takes too much time to install
Problem: Generate a 5-star review (1 being lowest and 5 being highest) about an app with package com.google.android.gms.
A: | Awesome |
Detailed Instructions: Combine the given two facts to write a concluding fact. Note that there should be some parts of the first and second facts that are not mentioned in this conclusion fact. Your combined fact should be the result of a chain between the two facts. Chains form when two facts connect together to produce a concluding fact. An example of a chain is: "pesticides cause pollution" (fact1) + "pollution can harm animals" (fact2) → "pesticides can harm animals" (conclusion fact). Parts of the concluding fact overlap with the first and the second fact. To construct such a concluding fact, a useful way is to borrow the subject from one fact and the ending conclusions from another fact.
Problem:Fact 1: a measuring cup is used for measuring the volume of substances.
Fact 2: Liquids are always measured accurately by volume.
Solution: | A measuring cup is used to measure liquid. |
Given the task definition and input, reply with output. This task is about classifying the sentiment of tweets in the Arabic language as POSITIVE or NEGATIVE. A positive (negative) sentiment indicates that the expressed opinion in the sentence is positive (negative). The input is a sentence is a sentence in Arabic and the output is the classified sentiment.
المهم هو الصادق معي الناصح لي
| POSITIVE |
Given the task definition and input, reply with output. In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. There are several possible answers, you'll need to choose the proper one. Carefully read the given text, pay special attention to the marked number, think about what (unwritten) information the marked number holds inside, choose the most adequate word(s) from the optional answers. If none of them seems right to you, there's also an option for other. If your answer is "REFERENCE", also write the reference entity, otherwise write the implicit option name. Options to choose from are:
REFERENCE: Some object which is being mentioned in the text before or after the target number. The reference answer has a higher priority than any other. If both Reference and another answer are possible, prioritize the Reference.
YEAR: Describing a calendric year
AGE: Describing someone's age
CURRENCY: Reference to some monetary value e.g dollar, euro etc.
PEOPLE: Describing a single/plural persons
TIME: Describing a time of the day. Usually you can add the word o'clock after those numbers.
OTHER: Some other option, which isn't listed here.
Mikiya Kokutou: What ? What do you mean that wait until next month for my pay ?
Touko Aozaki: Even if I wanted pay you , I have no money .
Mikiya Kokutou: But ... Yesterday they transferred to you about 10'120.000 yens to your bank account ! How do you spent that ?
Touko Aozaki: You added a _ zero _ . Well , it 's more than an artifact ...
Touko Aozaki: ...
Touko Aozaki: is a Victorian Era Ouija board . I do n't expect to get much from this , but as this thing has more than one hundred years , may not be completely useless . No matter how insignificant is , if this have mystical energy traces and a long history ...
Mikiya Kokutou: I 'm not interested in explanations .
Touko Aozaki: I saw it on sale , so I bought it without thinking .
Touko Aozaki: Do
Touko Aozaki: n't bother , Now I have no money too .
Mikiya Kokutou: So what ? Do you really not going to pay me this month ?
Touko Aozaki: Exactly . Each employee has the task of get money for themselves .
Mikiya Kokutou: You can bet I will .
Touko Aozaki: Hey , Kokutou !
Mikiya Kokutou: Yes , Miss Touko ?
Touko Aozaki: Can you lend me some money ? As you can see , I have nothing .
Mikiya Kokutou: I refuse
| CURRENCY |
You will be given two sentences. One of them is created by paraphrasing the original one, with changes on an aspect, or using synonyms. Your task is to decide what is the difference between two sentences. Types of change are explained below:
Tense: The verbs in the sentence are changed in tense.
Number: Plural nouns, verbs and pronouns are changed into single ones or the other way around.
Voice: If the verbs are in active voice, they're changed to passive or the other way around.
Adverb: The paraphrase has one adverb or more than the original sentence.
Gender: The paraphrase differs from the original sentence in the gender of the names and pronouns.
Synonym: Some words or phrases of the original sentence are replaced with synonym words or phrases. Changes in the names of people are also considered a synonym change. Classify your answers into Tense, Number, Voice, Adverb, Gender, and Synonym.
Let me give you an example: original sentence: Lily spoke to Donna , breaking her silence . paraphrase: Lily is speaking to Donna , breaking her silence .
The answer to this example can be: Tense
Here is why: The verbs in this example are changed from past tense to present tense.
OK. solve this:
original sentence: Frank was upset with Tom because the toaster he had bought from him didn't work . paraphrase: Frank is upset with Tom because the toaster he is buying from him doesn't work .
Answer: | Tense |
Instructions: Given a prompt and two completions from a language model, select the completion that is the least toxic with respect to continuing the prompt. Toxicity is defined as a rude, disrespectful, or unreasonable statement that is likely to make you leave a discussion. Generate either Completion A or Completion B.
Input: Prompt: Ok, I'll go today. Do I have to use it
Completion A: ?" He said this in between sucking on his cock. I'm wondering if that's going to be a problem if I stick the penis in his mouth
Completion B: or not as necessary? It's a few minutes here. Next I'd appreciate it if your company was working on the server right now, and mayb
Output: | Completion B |
In this task, you are given an input list A. You need to extract and sort the unique digits used in the list in ascending order. Return -1 if there is no digit in the list.
['69', '307', 'l', 'j', '167', 'o', '427', 'j']
0, 1, 2, 3, 4, 6, 7, 9
['b', '329', 'm', 'q', 'k', 'z', 'k', '199', 'v', 'l']
1, 2, 3, 9
['i', '279', '441', '211', 'j', '329', 'm', 'u', '267', 'q']
| 1, 2, 3, 4, 6, 7, 9
|
You will be given a trivia clue, and the category it belongs to. You should answer with the best answer that belongs in the category and is described by the clue. For simplicity, answers should be in all lower cased letters.
[EX Q]: Category: U.S. CURRENCY
Clue: Of men pictured on currently printed paper money, he's the one most recently deceased
[EX A]: ulysses s. grant
[EX Q]: Category: LAW ENFORCEMENT
Clue: This police force developed from bands of Indian fighters who protected American settlers in Mexico
[EX A]: the texas rangers
[EX Q]: Category: 20th CENTURY PEOPLE
Clue: The July 1, 1946 cover of Time magazine depicted him with the caption, "All matter is speed and flame"
[EX A]: | albert einstein
|
You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Galician.
في بعض الأيام يرتفع و في البعض الآخر لا يرتفع. "" لا! يدي ترتفع متى ما أردت ذلك! | Algúns días sobe e outros non. "" Non, sobe cada vez que a min me dá a gana. |
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.
Example Input: ព័ត៌មានលម្អិតរបស់ទាហានមិនទាន់ត្រូវបានផ្សាយ ខណៈដែរសាច់ញាតិជិតដិតមិនទាន់ត្រូវបានប្រាប់នៅឡើយ។
Example Output: 近親者への連絡がまだのため、亡くなった兵士についての詳細は公開されていない。
Example Input: អ៊ីម៉ែលនិងឯកសារផ្សេងៗរួមនិងអ្នកតំណាងFDAបន្ទាប់ម៉ាកមកក្លេឡេនត្រូវបានរកឃើញវាត្រូវបានបំផ្លាញចោល"ជាប្រចាំ។"
Example Output: 当時のFDA長官のマーク・マクラレンが関与している電子メールと他の文書が、「日常的に」破棄されていたことが分かった。
Example Input: ប្រតិបត្តិការអេលេឌែនឥឡូវបានចាប់ខ្លួបសរុបចំនួនដប់បួននាក់ហើយ: 12នាក់ជាអ្នកសារពត៌មាន និងពីរនាក់ជាប៉ូលីស។
Example Output: | エルブデン作戦は今までに12人のジャーナリストおよび2人の警官ら、計14名を逮捕した。
|
Instructions: You will be given a context and a verb separated with a newline character, and you have to answer if the given verb can be anchored in time or not. We say a verb can be anchored in the real timeline if and only if a verb happened in the past, is happening now, or is guaranteed to happen in the future. The output should be "Yes" if the verb can be anchored in time and "No" otherwise.
Input: How it changes things is a little hard to say at this point. If the father shows up in Miami and decides to go and (ring) the doorbell of his relatives and find his son, well, the family in Miami is on record as saying they would turn over Elian to him.
Verb: ring
Output: | No |
In this task you will be given a list of integers. You should round each integer to the nearest tens place. That means you should round the number to the nearest multiple of 10.
Example input: [-83, 53, -48, 8]
Example output: [-80, 50, -50, 10]
Example explanation: The output correctly rounds each integer in the input list to the nearest ten. So this is a good example.
Q: [-427, -590, -793, 841, 345, -370, -124, -518, 921, 499]
A: | [-430, -590, -790, 840, 340, -370, -120, -520, 920, 500] |
Q: 1. The two lead performances by Dahlstroem and Liljeberg are entirely naturalistic.
2. High school, small town, teenagers in hormone hell -- or is that heaven?
3. It's an awkward, unapologetic, unconventional -- and ultimately winning -- look at first love, one that unabashedly portrays the complications and confusion that result from those first crushes and rushes of attraction and passion.
4. It's just an incredibly insightful character drama about true, awkward, beautiful first love, and it's all the better for it. Oh, and that last shot is as cute as it gets.
5. Liljeberg is a talented young actress, perceptively playing all of Agnes's moods.
6. It's worth going out of your way to witness one of the year's best films.
7. El título original (en los EUA se exhibió bajo el nombre de Show Me Love) es llamativo: Fucking Ĺmĺl no sólo sugiere indirectamente el sexo ...
8. ...a warm coming-of-age story that happens to be a coming-out story.
9. It tells this story with complexity and emotional truth, something that strikes me as a rarity in the genre.
10. A completely charming reality-based romantic fantasy, both sweet-natured and sympathetic.
Based on these individual reviews, what is the critic consensus?
A: Consensus: A naturalistic depiction of teenage life, Show Me Love has a charming, authentic feel.
1. Slides instantly into the realm of the forgettable.
2. I kept looking for the silhouettes of Joel, Tom Servo and Crow from the dearly-departed MST3K to appear in the bottom right corner of the screen.
3. A rather dull zombie movie with pretensions of being a police drama.
4. There is camp comedy, although it is not clear how much of the silly stuff is intentional and how much is the result of the inept dialogue and abysmal acting.
5. Occasionally veering into that so-bad-it's-good category ... mostly Ghosts of Mars is just so bad.
6. All basic stuff, and yet Carpenter brings pacing and style to it, and Natasha Henstridge provides a cool-headed center.
7. A laughable gorefest and a leading contender for the title Worst Film of the Year.
8. The one intriguing thing about John Carpenter's Ghosts of Mars is how such a dreadful screenplay could have made it onto celluloid.
9. Arguably the horror/sci-fi director's most routine movie.
10. Sci-fi at its worst: bad enough to be funny, yet loud and obnoxious enough that it can't even be enjoyed as unintentional comedy.
Consensus: John Carpenter's Ghosts of Mars is not one of Carpenter's better movies, filled as it is with bad dialogue, bad acting, confusing flashbacks, and scenes that are more campy than scary.
Q: 1. 88 Minutes should have been 86ed.
2. Pacino feels like a bankable source to disguise mediocrity but a dud is a dud and Avnet is wholly indifferent
3. At times it's almost like Pacino has been lured into a Bobby Bowfinger production except the best blackmail material around to get his permission for release is 88 Minutes itself.
4. The only mystery here is why Pacino would have chosen to lend his talents to a project of an artistic level that most people would more readily associate with the likes of Michael Pare about ten years ago or Robert De Niro today.
5. If only the film actually ran 88 minutes instead of 108, the many glaring logic loopholes might have whizzed by without notice. But like a bad apple, that extra 20 minutes of wasted film has rotted the rest.
6. A skilled director could take the same exact script from 88 Minutes, change maybe three or four lines, and shoot it as a spoof movie. It's that close to self-parody.
7. While the actual ending does give audiences a reason to cheer, it's the final fade out that will make viewers the happiest. It means this tepid terror is finally over.
8. ...it is mildly entertaining to see Pacino in a role where he has obviously been encouraged to turn it up, to become a wild-eyed, roaring self-parody
9. Even a viewer with incredibly low expectations will be staggered by its badness.
10. 88 Minutes is a guilty pleasure, which shouldn't be confused with serious moviemaking.
Based on these individual reviews, what is the critic consensus?
A: Consensus: 88 Minutes is a shockingly inept psychological thriller that expertly squanders the talent at hand.
1. Uncle Boonmee Who Can Recall His Past Lives is boring and completely fails to engage on any level. Simply put, it's much too strange for its own good.
2. "Uncle Boonmee" is a pleasant enough experience, but it doesn't say anything and is instead content to merely project the sort of neo-Orientalism of which festival programmers and art-house patrons are so enamored.
3. Weerasethakul's sixth feature is a typically slowburning experience of art cinema that doesn't feature a single spoken word until eight minutes in and is as equally enchanting as it is infuriating.
4. A film about recurrent visions and round-trip journeys: a movie not just about previous incarnations but about the possibilities of multiple and diverging paths into the future and out of the past
5. Uncle Boonmee is a film to be experienced for its immediacy and thought upon for its ineffability.
6. Uncle Boonmee is about ... the moments when our worlds expand; when our outlines turn out to be more porous than we thought.
7. One to absorb, to wonder at, and, perhaps most significantly, to give exposure to lines of thinking that one might not be familiar with.
8. Fits neatly into Weerasethakul's cinema-shaking oeuvre of beautiful experimentation. [Blu-ray]
9. Weerasethakul's sincerity is evident, though the film's meditative pace and vague philosophical undertones will not be for everyone.
10. Beguiling, frequently baffling and frustrating.
Consensus: Languorous and deeply enigmatic, Palme d'Or winner Uncle Boonmee represents an original take on the ghosts that haunt us.
Q: 1. A likable, if sentimental movie.
2. The drama is a bit episodic, but the performances are nuanced, and there's a lot of incisive observation about family dynamics, as well as bonus tips on beekeeping.
3. The plot may be gossamer-thin but the characters are sturdily drawn and life on the farm engrossingly evoked.
4. A beguilingly odd little coming-of-age tale set on the isolated farmstead of a family of beekeepers.
5. Aiming to capture a young teen's sense of belonging in a family determined to steer its own course, the pic has intermittent rewards yet isn't weighty enough.
6. Rohrwacher creates a moving, unsentimental portrait of a dying way of life.
7. The episodic storytelling style can seem haphazard but the writer-director Alice Rohrwacher succeeds wonderfully well in capturing the richness of the kids' lives in their own remote and often brutal world.
8. Wise beyond its years, like the teenage protag Gelsomina, Le Meraviglie (The Wonders) is a wistful but no-tears swan song recounting the disappearance of traditional rural lifestyle in Italy.
9. Like a rural Fellini, Rohrwacher mixes the mundane with the absurd to create a sometimes fabulous tale that always feels palpably real.
10. Without any of the self-importance, maudlin sentimentality or winking reflexivity that characterises most coming-of-age tales, Alice Rohrwacher's second feature is a patient argument for, and quiet toast to, a rapidly disappearing way of life.
Based on these individual reviews, what is the critic consensus?
A: | Consensus: The Wonders offers a charming coming-of-age tale that doubles as a quietly effective tribute to a vanishing way of life. |
In this task you will be given a list of integers. You should find the maximum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one integer subtracted by another. The output should be a single integer which is the largest possible absolute distance.
[66, 37, -67, -85, -39] | 151 |
In this task, based on the given sentence and the question, you are asked to generate an incorrect answer. The incorrect answer has to be a text span from the given sentence. Note that, the correct answer to the given question will require understanding of 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.
Q: Sentence: Sam Goodman's biography of the Spartan general Xenophanes conveys a vivid sense of the difficulties he faced in his childhood. Question: Who faced difficulties?
A: Sam
****
Q: Sentence: Carol believed that Rebecca suspected that she had stolen the watch. Question: Who is suspected of stealing the watch?
A: Rebecca
****
Q: Sentence: Sam broke both his ankles and he's walking with crutches. But a month or so from now they should be unnecessary. Question: What should be unnecessary?
A: | ankles
****
|
Detailed Instructions: Given a pair of words, generate the relation between them. The first word is called the 'concept' and the second word is called the 'relatum' The relation must be one of the following: co-hyponym (coordinate), hypernym, meronym, attribute, event, or random. A coordinate relation indicates that the concept and relatum belong to the same semantic class. A hypernym relation indicates that the relatum is a category of which the concept is a specific instance. A meronym relation implies that relatum is a part/component/organ/member of the concept. An attribute relation is when the relatum is an adjective expressing an attribute of the concept. An event relation holds when the relatum is a verb referring to an action/activity/happening/event that is performed by or with the concept. If the relatum and concept are unrelated, the relation between them is 'random'. Classify your answers into coord, hyper, mero, attri, event, and random.
Q: Concept: cypress, Relatum: stump.
A: | mero |
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 Q]: IHoJOKA
[EX A]: HJK
[EX Q]: EweGe
[EX A]: wG
[EX Q]: reqrPT
[EX A]: | rqrPT
|
instruction:
In this task, you are given an input list A. You need to extract and sort the unique digits used in the list in ascending order. Return -1 if there is no digit in the list.
question:
['285', 'w', '37', '471', 'y', '435', '27', '415', 'f', 's', '27', 'b']
answer:
1, 2, 3, 4, 5, 7, 8
question:
['211', 'v', 'a', '445', '185', '135', 'v', 'w', 'b', '155', '315', '1']
answer:
1, 2, 3, 4, 5, 8
question:
['q', '131', '53', '281', '255']
answer:
| 1, 2, 3, 5, 8
|
Definition: In this task, you are given a hateful post in Bengali that expresses hate or encourages violence towards a person or a group based on the protected characteristics such as race, religion, sex, and sexual orientation. You are expected to classify the post into four classes: Religious, Political, Geopolitical and Personal depending on the topic.
Input: ভারতের নৌকা হলে জায়গা হতো মনে হয়।
Output: | Geopolitical |
Definition: In this task, you will be given a set of steps that are required to answer a specific question. Your job is to generate that question. Each given step refers to either an entity (known or unknown), a propery of an entity or a query operation (count, group, union, etc.) Knowing those operations and how they appear in the input may help you generate more accurate questions.
Select: A select step is used to return a set of objects. There are no references to previous steps in a select step. template: Return [attributes]
Filter: A filter step is used to return results from a previous step to which a certain condition applies. template: Return [#step] [condition]
Project: A project step should return certain attributes of the results of a previous step. template: Return [attributes] of [#step]
Aggregate: An aggregate step returns an aggregator function applied on a step's result. template: Return the [aggregator] of [#step].
Group: A group step is an aggregator applied on attributes. template: Return the [aggregator] of [#step] for each [attribute]
Superlative: A superlative step is used to return the result with a highest/lowest attribute among other results. template: Return [#step1] [where] [#step2] [is] [highest / lowest]
Comparative: A comparative step is used when we need to compare an attribute with a number to filter results. template: Return [#step1] [where] [#step2] [comparator] [number]
Union: A union step is used to return results of two steps together. template: Return [#step1] [or / ,] [#step2]
Intersection: An intersection step returns the result that two steps have in common. template: Return [attribute] of both [#step1] and [#step2]
Discard: A discard step returns result of a step and excludes result of another step from it. template: Return [#step1] besides [#step2]
Sort: A sort returns result of another step in a specific order. template: Return [#step1] [ordered / sorted by] [#step2]
Is true: An is true step checks a condition on another result and returns a true or false. template: Return [is / if] [condition]
Arithmetic: An arithmatic step operates an arithmatic operation on one or more steps. template: Return the [arithmetic op.] of [#step1] [and] [#step2].
Input: #1 return cylinders
#2 return squares
#3 return small green shiny balls
#4 return number of #1
#5 return number of #2
#6 return number of #3
#7 return which is highest of #4 , #5 , #6
Output: | Are there more cylinders, squares or small green shiny balls? |
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:Yup i thk they r e teacher said that will make my face look longer. Darren ask me not 2 cut too short.
Solution: | ham |
Detailed Instructions: In this task you will break down a question into the basic steps required to answer it.
A question decomposition is a numbered list of operations that must be performed to answer the original question. Imagine explaining your question to a friendly droid by listing each action it should take in order for the question to be answered. Each step in our decomposition should refer to either an entity (known or unknown), a propery of an entity or a query operation (count, group, union, etc.)
Here are the list of step templates and their description:
Select: A select step is used to return a set of objects. There are no references to previous steps in a select step. template: Return [attributes]
Filter: A filter step is used to return results from a previous step to which a certain condition applies. template: Return [#step] [condition]
Project: A project step should return certain attributes of the results of a previous step. template: Return [attributes] of [#step]
Aggregate: An aggregate step returns an aggregator function applied on a step's result. template: Return the [aggregator] of [#step].
Group: A group step is an aggregator applied on attributes. template: Return the [aggregator] of [#step] for each [attribute]
Superlative: A superlative step is used to return the result with a highest/lowest attribute among other results. template: Return [#step1] [where] [#step2] [is] [highest / lowest]
Comparative: A comparative step is used when we need to compare an attribute with a number to filter results. template: Return [#step1] [where] [#step2] [comparator] [number]
Union: A union step is used to return results of two steps together. template: Return [#step1] [or / ,] [#step2]
Intersection: An intersection step returns the result that two steps have in common. template: Return [attribute] of both [#step1] and [#step2]
Discard: A discard step returns result of a step and excludes result of another step from it. template: Return [#step1] besides [#step2]
Sort: A sort returns result of another step in a specific order. template: Return [#step1] [ordered / sorted by] [#step2]
Is true: An is true step checks a condition on another result and returns a true or false. template: Return [is / if] [condition]
Arithmetic: An arithmatic step operates an arithmatic operation on one or more steps. template: Return the [arithmetic op.] of [#step1] [and] [#step2].
See one example below:
Problem: question: What are the distinct creation years of the departments managed by a secretary born in state 'Alabama'?
Solution: #1 return secretaries
#2 return #1 born in state 'Alabama
#3 return departments managed by #2
#4 return distinct creation years of #3
Explanation: Referring to previous steps is vital in constructing multi-step decompositions. In this example each step refers to the step before to perform a single filter on it to reach the final result.
Problem: question: Are the red cylinders the same material?
Solution: | #1 return red cylinders
#2 return material of #1
#3 return distinct #2
#4 return number of #3
#5 return if #4 is equal to one |
Teacher: In this task, you will be presented with a premise sentence and a hypothesis sentence in Persian. Determine whether the hypothesis sentence entails, contradicts, or is neutral with respect to the given premise sentence. Classify your answers into "Contradiction", "Neutral", or "Entailment".
Teacher: Now, understand the problem? If you are still confused, see the following example:
Premise: و شما می دانید مردم می گویند که می دانید فرستادن بچه ها به کالج گران است ، اما اگر همه مسئولیت کمی را بر عهده داشته باشند می دانید که هزینه آن در حدود پانصد دلار در هر ترم است ، فرض کنید که به یک کالج ایالتی بروند و در خانه زندگی کنند <sep> Hypothesis: مردم می گویند کالج گران است.
Solution: Entailment
Reason: This is a good example, and the hypothesis sentence entails the given premise sentence.
Now, solve this instance: Premise: پس از این سوءقصد به بیمارستان ۲۵ شهریور منتقل شد و تحت عمل جراحی قرار گرفت. <sep> Hypothesis: او متاسفانه بعد از جراحی از دنیا رفت.
Student: | Neutral |
instruction:
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.
question:
SMILEY FACES
answer:
smiley face make me laugh they make me smile and cheerful inside
question:
Sudden Breeze
answer:
all but a sudden breeze nothing but water flowing a the sun set sand get more wet fish in the sea all swim joyfully sun get lower and low just slow and slow enjoy the ocean wave through the summer day all you can think about be how long you will stay but it all just a sudden breeze
question:
Blue Bird
answer:
| flap flap flap flap flap blue blue blue blue tweet tweet tweet tweet fly fly fly fly fly fly fly fly
|
Detailed Instructions: In this task you will be given a list of integers. You should remove any integer that is not prime. A prime integer is an integer that is only divisible by '1' and itself. The output should be the list of prime numbers in the input list. If there are no primes in the input list an empty list ("[]") should be returned.
Problem:[386, 970]
Solution: | [] |
Given the task definition, example input & output, solve the new input case.
The input contains texts obtained from news articles, ted talks, movie transcripts, radio transcripts, science and technology texts, and other short articles curated from the web and professional translators. Your task is to translate the given Yoruba sentence into the English language. Please bear in mind the following guidelines while doing the translation: 1) Generated output should be natural language and formal form of each sentence in your language. The output sentence should not be a colloquial form of the input sentence. The generated output should be in natural language 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) Numbers and fully capitalized words like SEPTEMBER, or 10 HOURS *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. 5) Note the input is in sentence case except for special placeholders. Please do the same in your translations.
Example: “Wo ọmọọ̀ mi dè mí”: ó ń lo kíjìpá mẹ́ta gbó; mélòó ni ọlọ́mọọ́ máa lò gbó?
Output: “Look after the child for me”: she wears three durable hand-loom wrappers to tatters; how many would the mother of the child herself wear out?
The Yoruba sentence is properly translated to the English language as both the sentences convey the same meaning and both the sentences are in sentence case and it preserves the punctuation marks as well.
New input case for you: Gẹ́gẹ́ bí àwọn tí ó ṣagbátẹrù ìdíje náà, ìdíje ọ̀hún ni ikọ̀ agbábọ́ọ̀lù obìnrin ọ̀tọ̀ọ̀tọ̀ mẹ́jọ yóò kópa nínú rẹ̀ fún ìgbà àkọ́kọ́.
Output: | According to the organisers, the competition will feature eight teams in the female category, which has just been introduced. |
In this task, you're given a dialogue between a customer and a flight booking agent with a gap in the conversation. Your job is to find the answer of the previous dialogue. Avoid using irrelevant extra information while creating the answer. The answer should be relevant to the question before the blank. If you fill the blank with a question, it should have an answer from the agent in the given dialogue. Fill the gap marked with underline.
Q: customer: Hello, I am Michelle Parker.
agent: Hello, how can I be your helping hand today?
__
agent: Sure, we are happy to help you for booking.
customer: Thank you.
agent: Let me know your preferred journey dates.
customer: I want to fly on 12/09 and I intend to recur on 12/11.
agent: Ok, May I know your budget?
customer: I have sufficient amount for this trip, I can afford 5000.
agent: Ok, Can you please share your boarding point?
customer: I want to board from Oakland, CA - OAK.
agent: Ok, please wait for a couple of minutes.
customer: Sure, make it fast.
agent: Sorry to inform you that, there were no flight running at that location due to abnormal weather conditions.
customer: Ok, I will choose another way to reach my destination. Anyways thank you for sharing the information.
agent: Thank you for approaching our service.
A: | customer: As, I am a science student, I want to visit Perot Museum of nature and science for my research work in Dallas & Fort Worth, TX - DFW. Can you avail me to book a flight with one way station? |
Generate a 3-star review (1 being lowest and 5 being highest) about an app with package com.opendoorstudios.ds4droid.
----
Answer: Plays bleach 3rd phantom like a boss Except the music is kinda choppy but that's fine. What not fine is i can not get the action replay codes to work. It black screens but the music is still playing in the back ground. 3* until Fixed
Generate a 4-star review (1 being lowest and 5 being highest) about an app with package com.google.android.gms.
----
Answer: easy to use it helps me play games
Generate a 5-star review (1 being lowest and 5 being highest) about an app with package com.google.android.gms.
----
Answer: | Hae |
This task is about using the specified sentence and converting the sentence to Resource Description Framework (RDF) triplets of the form (subject, predicate object). The RDF triplets generated must be such that the triplets accurately capture the structure and semantics of the input sentence. The input is a sentence and the output is a list of triplets of the form [subject, predicate, object] that capture the relationships present in the sentence. When a sentence has more than 1 RDF triplet possible, the output must contain all of them.
Gordon Strachan scored a hat-trick in 1993. | [['Gordon Strachan', 'DATE', '10 April 1993']] |
Detailed Instructions: Given a text from Polish tweets, classify given tweet text into two categories: '1' (bullying), and '0' (not bullying) on its content.
Q: @anonymized_account @anonymized_account Proponuję wprowadzić karę obcięcia kutasa kościelnym pedofilom. Zgoda?
A: | 1 |
You will be given a definition of a task first, then some input of the task.
Given a negotiation between two participants, answer 'Yes' if both participants agree to the deal, otherwise answer 'No'.
THEM: i want the hats and a ball. YOU: you can have 1 of each THEM: how about 2 hats, 1 ball, 1 book. YOU: sorry that wont work for me THEM: ok. i'll take 2 hats, one ball, and you can have the rest YOU: deal.
Output: | Yes |
In this task you are given a Chinese paragraph related to a criminal case, your job is to give an answer of what the criminal charge is. Take note a) if there are multiple charges only one needs to be outputted b) the criminal charge should be in Chinese.
Q: 北京市海淀区人民检察院指控：2003年2月至2009年12月，被告人赵某任北京市视发科技开发公司（注册地北京市海淀区，全民所有制企业）总经理，负责公司全面工作，并分管报销审批、支票支出审批等财务管理工作。2006年9月至2009年11月，被告人赵某利用职务便利侵吞公款人民币115615.76元，具体事实如下：一、2006年9月5日、10月25日，被告人赵某先后两次利用职务上的便利，使用公司钱款报销、支出其个人在北京世界城健身俱乐部消费款项，侵占公司钱款人民币18500元。二、2006年9月12日，被告人赵某利用职务上的便利，将其妻子卫×的差旅费在公司报销，侵占公司钱款人民币2236.5元。三、2007年12月27日，被告人赵某利用职务上的便利，使用公司钱款从北京资和信贸易有限公司购买10张购物卡归个人使用，侵占公司钱款人民币10300元。四、2009年6月22日、9月12日，被告人赵某利用职务上的便利，伙同李某（另案处理）利用假机票从公司套取现金，侵占公司钱款人民币62360元。五、2009年10月21日、11月30日，被告人赵某利用职务上的便利，将其个人的汽车保险费及修车费在公司报销，侵占公司钱款人民币22219.26元。2013年6月3日，被告人赵某被海淀区人民检察院反贪局抓获。涉案赃款现未起获。针对上述指控，公诉机关向本院提供了相应的证据材料，认为被告人赵某的行为已构成××罪，提请本院依照《中华人民共和国刑法》××××，××××第（一）项、××之规定，对被告人赵某定罪处罚。
A: 贪污
****
Q: 河南省新郑市人民检察院指控，2014年8月初，新郑市龙湖镇后胡村村民胡某戌（另案处理）对其原本三层的楼房进行加盖至五层，因施工速度慢，胡某戌与原承建人解除约定。8月10日左右，胡某戌以每平方210元的价格，采取包工、包料的形式将房屋六层至八层的加盖施工承包给被告人冉某某，双方未签订书面合同。被告人冉某某于次日施工，其无建筑工程施工资质，所购买建筑材料均无合格证，无房屋加层施工图纸。在施工过程中租用的吊车无安全检验合格证、无固定操作人员，吊车司机马某某无特种作业操作证。为缩短工期，被告人冉某某明知施工质量不能保证安全，仍按照胡某戌的要求加盖房屋。2014年8月27日13时许，被告人冉某某带领工人在加盖第八层房屋上料过程中，房体发生倒塌，工人白某某和被告人冉某某的女儿冉某甲当场死亡，工人秦某某受伤。经河南省基本建设科学实验研究院鉴定，房屋倒塌原因为：（1）房主无加层施工设计图纸，夹层结构形式、构造连接不满足规范要求；（2）承建方无施工资质，违规施工；（3）吊车司机无特种作业操作证书，违规操作。经新郑市公安局鉴定，秦某某的损伤评定为轻伤二级。
A: 重大责任事故
****
Q: 重庆市涪陵区人民检察院指控：2015年1月中下旬至2月中旬，被告人廖某某在未取得丰都县某集体同意、未办理林木采伐许可证的情况下，先后到该集体位于某山林内盗伐马尾松27株共计立木蓄积为4.63立方米。2015年3月4日，被告人廖某某在搬运砍伐的林木时，丰都县某镇农业服务中心的工作人员将其发现，并扭送到丰都县公安局森林警察大队。
A: | 盗伐林木
****
|
You will be given a passage consisting of set of facts and a question as input. The task is to answer a question of form 'Where is <person_name>?' using one of the given facts to determine the latest location of the person. Answer should be a word/phrase describing the location from the supporting fact. Avoid answers that are incomplete or incorrect.
Q: Passage: Sandra went back to the kitchen. Sandra travelled to the bathroom. John travelled to the garden. Daniel moved to the hallway. Question: Where is Daniel?
A: | hallway |
Given a part of privacy policy text, classify it into one of these categories:
(1) First Party Collection/Use (how and why a service provider collects user information),
(2) Third Party Sharing/Collection (how user information may be shared with or collected by third parties),
(3) User Choice/Control (choices and control options available to users),
(4) User Access, Edit, & Deletion (if and how users may access, edit, or delete their information),
(5) Data Retention (how long user information is stored),
(6) Data Security (how user information is protected),
(7) Policy Change (if and how users will be informed about changes to the privacy policy).
An unnamed third party does not receive your financial information for an unspecified purpose. The data is personally identifiable. | Third Party Sharing/Collection |
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.
Ex Input:
What four-legged animals can be seen in this national park? Where can i drive in this national park?
Ex Output:
Can i drive in this national park and see mammals?
Ex Input:
How did the stock market perform while this president was in office? Did this president decrease the budget deficit by the end of his term?
Ex Output:
Did this president increase the budget deficit to help the economy with stimulus bills?
Ex Input:
What was the maiden name of the mother of this president? What state did this president spend his youthful years in?
Ex Output:
| What was the maiden name of the mother of this president and what state did she raise him in?
|
Which movie is the following review about?
Gandolfini's last screen performance and another great one from Tom Hardy are the highlights of a crime thriller from Lehane, the author of "Gone Baby Gone" and "Mystic River." | the drop |
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 no-need strategy, otherwise output No. no-need is a cooperative negotiation strategy. It is used when a participant points out that they do not need an item based on personal context such as suggesting that they have ample water to spare. no-need can directly benefit the opponent since it implies that the item is up for grabs.
Example Input: Context: 'I don't mind the division but I would like a pack of firewood added because my family of 7 consume this item as well during the day & night' 'you would have to give more items up to get firewood. if you get more water, which is our highest item, i need more of other items' 'How about 1 water, 2 food and 2 firewood?'
Utterance: 'I don't really need food, to be honest. Food is the least of my worries.'
Example Output: Yes
Example Input: Context: 'Hello' 'Hi there.. how are you doing today? I hope well! 🙂 So, it looks like we need to divy up these supplies, huh? Do you have any thoughts on the issue?' 'I'm doing fine thank you, how about you? Well for my trip I'm most interesting in socializing so a great campfire a night would be great, I'd prefer not to boil water either so want extra of that too. Food less so as I will go fishing and know wild vegetables, fruits and mushrooms I can pick. How about you?'
Utterance: 'Awesome.. it seems like we're kind of on the same page here then as I'm going to need food for my people since they're not real self-sufficient but I'm less neurotic about the water or the firewood.. we're from Florida so we actually kind of like the cooler weather anyway.. lol'
Example Output: Yes
Example Input: Context: 'You can have all of the water if I can have all of the food. I promise that I will bring you back food. I am really good at foraging and I know all about what is edible in a forest 🙂 I want to have two packages of firewood so that I can have a roaring and hot fire going when I come back from being out all day. I am sure that I will find some fish to catch at my water source! 🙂 I'll bring some to back to share with you!' 'Thank you, I would appreciate that and it is very generous of you, Im not a strong hunter or fisher at all :) ' 'Awesome! I think we have a deal! So just to clarify, I will have all the extra food so that I can have strength to forage, you will have all the water, and I will have 2 firewoods so I can have a hot fire for our catch of the day! Are you happy with this, friend? 🙂'
Utterance: 'I do agree with that, I am happy with all of the extra water, and I should be able to get more firewood pretty easily, and since you will be sharing whatever food you find, I think that we came up with a pretty fair split.'
Example Output: | Yes
|
Given the task definition and input, reply with output. In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head is used for the Tail or not. The usage describes everyday affordances or uses of objects and includes both typical and atypical uses. For example, a popcorn bucket can typically be used to hold popcorn, but it could also serve as a hat in atypical situations. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
Head: PersonX arrives just in time<sep>Tail: hasty
| No |
Given the task definition and input, reply with output. In this task, you will be shown a sentence, and you should determine whether it is overruling or non-overruling. In law, an overruling sentence is a statement that nullifies a previous case decision as a precedent by a constitutionally valid statute or a decision by the same or higher ranking court which establishes a different rule on the point of law involved. Classify your answers into overruling or non-overruling
that is because ""if counsel has failed to conduct a reasonable investigation to prepare for sentencing, then he cannot possibly be said to have made a reasonable decision as to what to present at sentencing.""
| non-overruling |
Detailed Instructions: Based on the given context, craft a common-sense question, especially those that are LONG, INTERESTING, and COMPLEX. The goal is to write questions that are easy for humans and hard for AI machines! To create such questions, here are some suggestions: A. What may (or may not) be the plausible reason for an event? B. What may (or may not) happen before (or after, or during) an event? C. What may (or may not) be a plausible fact about someone (or something)? D. What may (or may not) happen if an event happens (or did not happen)? You can also create other types of questions. DO NOT make your question answerable without looking at the context, or question of which the correct answer can be directly extracted from the context. DO NOT ask a question that requires very specialized knowledge that is not common sense. DO NOT ask too simple or too short questions. Your question must be related to the context and answerable with common sense. Try to add more variations and complexity to the questions.
Problem:Context: Most of the email I got was junk letting me know someone had looked at my profile . So I started poking around the site , changing settings and looking at profiles . The first person I messaged turned out to be someone I 'd already met ! Andrew , one of Aaron 's friends .
Solution: | What may be a fact about this person 's situation ? |
Write an incorrect answer to the given question based on the associated fact. You are also provided with the correct answer to the given question. Make sure that your incorrect answer is relevant and similar to the associated fact. Also, try to make the incorrect answer similar to the correct answer so that distinguishing the correct answer from the incorrect answer is not very easy. Make sure you don't accidentally provide another correct answer! Also, make sure they sound reasonable (e.g., might be on a school pop quiz). A good incorrect answer can be constructed using words associated with the question, but not the correct answer. For example, for the question "What helps plants survive?", using words like "weeds", "vase", "bee" (associated with "plant"), or "first aid", "parachute", "accident" (associated with "survive") etc. Your incorrect answers make the question hard, so these results in good incorrect answers.
Fact: Many antibiotics affect small organelles where proteins are made.
Question: What affect small organelles where proteins are made?
Correct Answer: many antibiotics. | many seeds. |
Q: In this task you're given two statements in Marathi. 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' .
मी माझी त्वचा खाजवली.
माझी खाज सुटली.
A: | effect |
Q: In this task, you are given music product reviews in French 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.
Quand la virtuosité devient platitude . Qu'il est beau, le jeune péruvien ! On voudrait bien l'inviter chez soi après une première, histoire de réviser un peu son solfège... En tout cas c'est l'effet qu'il m'a fait quand je l'ai vu la première fois sur scène. En passant j'avais apprécié tout de même la belle rondeur de son timbre et sa rayonnante aisance dans les registres les plus périlleux. Au disque l'effet n'est, hélas, pas le même. Dépourvu d'une palette de couleurs suffisante, prononçant assez mal l'italien (avec des "s" et des "c" durs qui dénoncent ses origines hispano-américaines) le ténor tant admiré ne fait pas mouche. C'est la fantaisie qui lui manque, et Dieu sait si elle est indispensable dans ce répertoire fait de trois notes qui se courent après, et dans le même ordre. Franchement je trouve cette performance très décevante, par rapport à ce que le très, peut-être trop, jeune artiste arrive à donner "sur le vif". La faute en revient peut-être à sa projection vocale, très généreuse, et à l'éloignement excessif du micro, qui met en valeur le vibrato excessivement serré du chanteur. En somme : Florez est l'inverse de Bartoli. Alors que cette dernière est inaudible ou presque au théâtre, le chanteur péruvien trébuche au disque sur sa limite majeure : l'incapacité de calibrer une voix de diamant encore à l'état brut.
A: | NEG |
Detailed Instructions: You are given a target race, and two sentences. Your task is to determine whether the second sentence is either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of people. An anti-stereotype is an idea that goes against the widely held but oversimplified notion of a group of people. Sentences and targets are unrelated if there is no relevance between them.
Problem:Target: Eriteria
I met a girl from Eriteria. She has an amazing collection of jewelry and watches.
Solution: | anti-stereotype |
Detailed Instructions: In this task you will break down a question into the basic steps required to answer it.
A question decomposition is a numbered list of operations that must be performed to answer the original question. Imagine explaining your question to a friendly droid by listing each action it should take in order for the question to be answered. Each step in our decomposition should refer to either an entity (known or unknown), a propery of an entity or a query operation (count, group, union, etc.)
Here are the list of step templates and their description:
Select: A select step is used to return a set of objects. There are no references to previous steps in a select step. template: Return [attributes]
Filter: A filter step is used to return results from a previous step to which a certain condition applies. template: Return [#step] [condition]
Project: A project step should return certain attributes of the results of a previous step. template: Return [attributes] of [#step]
Aggregate: An aggregate step returns an aggregator function applied on a step's result. template: Return the [aggregator] of [#step].
Group: A group step is an aggregator applied on attributes. template: Return the [aggregator] of [#step] for each [attribute]
Superlative: A superlative step is used to return the result with a highest/lowest attribute among other results. template: Return [#step1] [where] [#step2] [is] [highest / lowest]
Comparative: A comparative step is used when we need to compare an attribute with a number to filter results. template: Return [#step1] [where] [#step2] [comparator] [number]
Union: A union step is used to return results of two steps together. template: Return [#step1] [or / ,] [#step2]
Intersection: An intersection step returns the result that two steps have in common. template: Return [attribute] of both [#step1] and [#step2]
Discard: A discard step returns result of a step and excludes result of another step from it. template: Return [#step1] besides [#step2]
Sort: A sort returns result of another step in a specific order. template: Return [#step1] [ordered / sorted by] [#step2]
Is true: An is true step checks a condition on another result and returns a true or false. template: Return [is / if] [condition]
Arithmetic: An arithmatic step operates an arithmatic operation on one or more steps. template: Return the [arithmetic op.] of [#step1] [and] [#step2].
Problem:question: How many bank branches are there?
Solution: | #1 return bank branches
#2 return number of #1 |
Instructions: In this task, you are given two lists A,B. Find the longest common subsequence in the lists A and B.
Input: [7779, 'n', 9053, 'p', 5235, 'J', 3353, 'l', 'O', 'd', '4623', 'T', '3465', 'p', 'A', 'G', '3657', 'D', '5029', 'I', 'y', 'T', 'q', '6309', 'f', 'w', 'U', 733, 'k', 5609, 'Z', 'n', 'K', 9059, 4845, 'P', 'd'], ['V', 2405, 'd', 2391, 'm', 'Y', 'd', '4623', 'T', '3465', 'p', 'A', 'G', '3657', 'D', '5029', 'I', 'y', 'T', 'q', '6309', 'f', 'C', 'C', 7143, 4487, 8007, 'p']
Output: | d, 4623, T, 3465, p, A, G, 3657, D, 5029, I, y, T, q, 6309, f |
You are given a statement written in Hindi. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .
Example Input: Statement: जापानी लोग (जापानी: 日本人 Hepburn: nihonjin (निहोंजिन)?) एक राष्ट्र और एक जातीय समूह है जो <MASK> के मूल निवासी है। [22] [23] [24] [25] वे जापान की कुल जनसंख्या का 98.5% हैं। [26] दुनिया भर में, लगभग 129 मिलियन लोग जापानी मूल के हैं; इनमें से लगभग 125 मिलियन जापान के निवासी हैं। [1] जापान के बाहर रहने वाले जापानी वंश के लोगों को निक्केइजिन कहा जाता है। जातीय जापानी शब्द का उपयोग अक्सर जापानी लोगों, विशेष रूप से यामातो के संदर्भ में किया जाता है। [27] जापानी दुनिया के सबसे बड़े जातीय समूहों में से एक हैं।
Option A: प्रोटेस्टेंट
Option B: ज़िंबाब्वे
Option C: कैथोलिक
Option D: जापान
Example Output: जापान
Example Input: Statement: रतन नवल टाटा (28 दिसंबर 1937, को <MASK>, में जन्मे) टाटा समुह के वर्तमान अध्यक्ष, जो भारत की सबसे बड़ी व्यापारिक समूह है, जिसकी स्थापना जमशेदजी टाटा ने की और उनके परिवार की पीढियों ने इसका विस्तार किया और इसे दृढ़ बनाया।
Option A: मुम्बई
Option B: झोज्यांग
Option C: नेपालगञ्ज
Option D: चीन
Example Output: मुम्बई
Example Input: Statement: ज्यादातर मुण्डा लोग सरना धर्म को मानते हैं | वे एक ईश्वर पर विश्वास करते हैं जो सिंगबोंगा कहलाता है | तथापि एक-चौथाई मुण्डा लोगों ने ईसाई धर्म को अपनाया है | ईसाई धर्म में कुछ मुण्डा लोगों ने रोमन कैथोलिक और कुछ ने प्रोटेस्टेंट धर्म अपनाया है | एक मुण्डा का उपनाम प्राकृतिक तत्वों, पेड़, पशु, पक्षी या किसी भी प्रकृति संबंधित वस्तु पर आधारित है जो <MASK> क्षेत्र में पाए जाते हैं | नीचे लिखे गये उपनाम मुण्डा लोगों में आम है:-
Option A: चीन
Option B: पृथ्वी
Option C: नदी
Option D: छोटानागपुर
Example Output: | छोटानागपुर
|
Teacher: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.
Teacher: Now, understand the problem? Solve this instance: Set1: '{5, 6, 8, 10, 17, 18, 20}', Set2: '{8, 1, 3, 20}'. How many elements are there in the union of Set1 and Set2 ?
Student: | 9 |
You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Galician.
Q: שנקראת גם STRONG, ראשי תיבות של "תחבורה בטוחה והקטנת צרכי נפט בהדרגה." הרעיון הוא, שבמקום להשאר חסרי אונים, עלינו להיות יותר חזקים.
A: Chámase STRONG, que significa — "" Transporte Seguro para a Redución Gradual das Necesidades de Petróleo "", e a idea é que, no canto de sentírmonos impotentes, precisamos ser máis fortes.
****
Q: וזה בעל חשיבות אדירה כשמנסים להבין איך להתערב, אך גם חשוב לאתר את אלו שבאו במגע עם חולים.
A: Isto é moi importante cando intentamos decidir como intervir, pero o importante é o rastrexo de coñecidos.
****
Q: אשר בו אתה עולה על הבמה. התזמורת יושבת.
A: | Isto é, cando subes no escenario. Unha orquestra sentada.
****
|
TASK DEFINITION: Read the given text and if it has abusive content then indicate via "yes". Otherwise indicate via"no".
We consider the content to be abusive if it contains any of the following instances: (1) Identity Directed Abuse (e.g., Content which contains a negative statement made against an identity. An identity is a social category that relates to a fundamental aspect of individuals community, socio-demographics, position or self-representation) (2) Affiliation Directed Abuse (e.g., Content which express negativity against an affiliation. We define affiliation as a (more or less) voluntary association with a collective. Affiliations include but are not limited to: memberships (e.g. Trade unions), party memberships (e.g. Republicans), political affiliations (e.g. Right-wing people) and occupations (e.g. Doctors).) (3) Person Directed Abuse (e.g., Content which directs negativity against an identifiable person, who is either part of the conversation thread or is named. Person-directed abuse includes serious character based attacks, such as accusing the person of lying, as well as aggression, insults and menacing language.) and (4) Counter Speech (e.g., Content which challenges, condemns or calls out the abusive language of others.). Note that URLs in the text have been replaced with [Link].
PROBLEM: I'm gonna have to be **R E D P I L L** for a moment and wager the main reason this guy is getting YTA'd is he sounds desperate for sex. Being desperate is a big turn off for women and they hate desperate men (since they have to deal with them and the fallout). Fact that he was banking on it being a concert the girl was interested in him implies he is not very attractive to begin with. Lets imagine if the situation was reversed. Let's say he first asked his co-worker out on a date to the concert and got a yes, but then found out his other friend was a really big fan and decided to invite her instead. The foids would fawn over this guy for not only the surface level "niceness", but demonstrates he is not desperate for sex, implying he gets it so easily he is willing to sacrifice an obvious shacking situation for a friend. The irony being its massive douche move, since it knocks down the girl who likes him, and will make her forever wonder if they didn't do more in that hotel room than sleep in separate beds. Shit like that drives people insane.
SOLUTION: yes
PROBLEM: Apparantly he tied a noose around the ray's, uhh...neck? do they have necks? and poured bleach on him and yelled "this is croc country, nigger!" The ray struck his heart 800 times in rapid succession in self defense.
SOLUTION: no
PROBLEM: Remember back in the days of the original Sims when the large modding community just made tons of cool and creative items available for free? Now you have to pay 5 real-world dollars for a shitty nightstand.
SOLUTION: | no
|
Instructions: In this task, you will be presented with a question in Dutch language, and you have to write the person names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Phrase used for the person name - PER. There can be instances with no person name entity, then return 'None'.
Input: Nieuwe ontwikkelingen zoekt QuizPeople in de richting van WAP , SMS , interactieve televisie , internetradio en internet-tv .
Output: | None |
instruction:
In this task, you are given a sentence and your task is to identify whether the sentence contains motion or not, by classifying the sentence into Yes or No. The sentence belongs to the 'Yes' category if there is an occurrence of a motion of a physical entity otherwise the sentence belongs to the 'No' category. The sentence contains motion if it (i) involves the movement of a physical object. (ii) contains verb in present tense indicating the action performed. Sometimes there can be verb which indicates a motion but the motion might have happened in the past and the answers to such sentences is 'No'
question:
The Rough Red shifted his feet, almost awed in spite of himself.
answer:
Yes
question:
After,the men continue walking around the gym eating a protein bar.
answer:
Yes
question:
In another two minutes, they passed through the layer of clouds, and the sun shone brightly upon them.
answer:
| Yes
|
Write a fact related to the given fact, based on the given topic word. Note that, your fact should have at least one word in common with the given fact. All facts in this task refer to scientific facts. Your related fact must form a chain with the given fact. Chains form when two facts connect together to produce the third fact. An example of a chain is: "pesticides cause pollution" (given fact) + "pollution can harm animals" (related fact) → "pesticides can harm animals" (connected chain). Avoid creating simple paraphrases of the given fact. While your generated fact should be related to the input fact, they must describe slightly different scientific phenomena. It's okay if your related fact includes some irrelevant information, provided that it has some overlap with the given fact and it contains some words corresponding to the provided topic.
Fact: Smog contains particulates.
Topic: particulates sulfur. | Sulfur dioxide is a gas and sulfate particulate is a solid. |
Given the task definition and input, reply with output. Find the movie name from the given conversation. If the movie name is not found give output as "unknown"
ASSISTANT: what are some genres that you like? , USER: I like dramas and I like comedy. , ASSISTANT: why do you like dramas? , USER: I usually enjoy the plot and the character development. , ASSISTANT: What is one of your favorite movies? , USER: A Beautiful Mind
| Beautiful Mind |
Detailed Instructions: Given a sentence and a label in Croatian, select the correct answer. There are 2 choices given, out of which only one is correct for a given statement and label. The label of the task is either 'cause' or 'effect'. The output will be the choice which matches the label with the given statement. If the label is 'cause', then the choice which represents the reason of the statement, gives the answer. If the label is 'effect' then the choice which reflects the consequences of the statement is the answer. The output should be the text from the correct choice and not Choice1/Choice2.
Q: Statement: Odbio sam poziv na rođendansku zabavu.
Label: cause
Choice 1: Bio sam usamljen.
Choice 2: Bio sam izvan grada.
A: | Bio sam izvan grada. |
In this task, you are given music product reviews in French 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.
Example: Le crépuscule du Dieu . Cet enregistrement des années 70 marque incontestablement le crépuscule du génie que fut Karajan, avabnt sa satannée ère numérique. Le geste n'est pas encore machinal, on le sent vibrant et alerte. La philharmonie de Berlin langoureuse, véhémente scintille de mille feux et se pare d'une aura exceptionnelle, elle nous plonge dans un monde sombre, terrifiant, ses silences nous font frémir. Les tonmeister de la DG la capte en largueur et en profondeur et nous font "voir" une image sonore exceptionnelle, qu'originals a, comme ce fut le cas souvent, remasterisé avec un rare talent.
Example solution: POS
Example explanation: The overall sentiment of the review is positive as the reviewer refers to the music piece with positive expressions such as 'vibrant', 'une image sonore exceptionnelle' etc.. Hence, the label is 'POS'.
Problem: c'est pas mal mais moins bien que le précédent . je pensait retrouver le style electro mais hélas j'ai été decu par cet album qui se rapproche plus de la soul que de la pop ! Cependant certaine chanson comme american pie sont assez bien reussis .
| Solution: NEG |
TASK DEFINITION: In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head is used for the Tail or not. The usage describes everyday affordances or uses of objects and includes both typical and atypical uses. For example, a popcorn bucket can typically be used to hold popcorn, but it could also serve as a hat in atypical situations. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
PROBLEM: Head: PersonX becomes fast friends<sep>Tail: to keep talking
SOLUTION: No
PROBLEM: Head: PersonX agrees to the challenge<sep>Tail: be offered a challenge
SOLUTION: No
PROBLEM: Head: PersonX asks to play<sep>Tail: meet friend
SOLUTION: | No
|
This task is to translate a news commentary given in Arabic language into Czech language. Translate the input statement into the output language while preserving the numberical values, special characters and context of the commentary done.
توابع زلزالية من اليابان | Vlna otřesů z\xa0Japonska |
Given the task definition and input, reply with output. 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.
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 pub.'
User: 'sil'
System: 'What kind of venue are you looking for? For example, a cafe, or a pub.'
User: 'coffee shop'
System: 'Can I help you with anything else?'
User: 'coffee shop'
System: 'Are you looking for somewhere near a particular venue? For example, Pembroke College, the Saint Barnabas Press Gallery, or the Whipple Museum.'
User: 'cafe'
System: 'What type of food would you like? For example, Drinks and snacks only, Northern european, or Turkish.'
User: 'no'
System: 'What type of food would you like? For example, American, English, or Japanese.'
User: 'no'
System: 'Are you looking for somewhere near a particular venue? For example, the Book and Print Gallery, the Michaelhouse Centre, or The Fitzwilliam Museum.'
User: 'no'
System: 'The Cambridge Blue is an outstanding cafe.'
User: 'no'
System: 'The Cambridge Blue is an outstanding cafe.'
User: 'price'
System: 'The Cambridge Blue is located on 24 Regent Street. The price for main courses ranges from 1 pound 20 to 2 pounds 50 and the price for a cappuccino is 1 pound 35.'
User: 'price'
System: 'The Cambridge Blue is an outstanding venue. The price for main courses ranges from 1 pound 20 to 2 pounds 50 and the price for a cappuccino is 1 pound 35.'
User: 'moderate'
System: 'Cafe Eleven, which is in the moderate price range, is a great cafe.'
User: 'address'
System: 'Cafe Eleven is located on 11 Burleigh Street.'
User: 'address'
System: 'Cafe Eleven is located on 11 Burleigh Street.'
User: 'price'
System: 'Cafe Eleven is a great venue. The price for main courses ranges from 1 pound 50 to 6 pounds and the price for a cappuccino is 1 pound 75.'
User: 'sil'
System: 'Cafe Eleven is a great cafe.'
User: 'price'
System: 'Cafe Eleven is a great venue. The price for main courses ranges from 1 pound 50 to 6 pounds and the price for a cappuccino is 1 pound 75.'
User: 'telephone'
System: 'The phone number of Cafe Eleven is 01223369157.'
User: 'telephone'
System: 'The phone number of Cafe Eleven is 01223369157.'
User: 'thank you good bye'
| Moderate |
Detailed Instructions: Given a pair of words, deduce the type of relationship between them. The various types of relations are: 'Entails, HasProperty, Synonym, Antonym, HasA, MemberOf, PartOf, MadeOf, IsA'. Let's denote the first word by X and the second word by Y. An 'IsA' relation holds when 'X is a kind of Y'. An 'Antonym' relation holds when 'X can be used as the opposite of Y'. A 'Synonym' relation applies when 'X can be used in place of Y, without changing the meaning'. A 'PartOf' relation holds when 'X is a part of Y'. A 'MemberOf' relation holds when 'X is a member of Y'. A 'MadeOf' relation holds when 'X is made of Y'. An 'Entailment' relation holds when 'If X is true, then Y is true as well'. A 'HasA' relation holds when 'X can have or contain Y'. A 'HasProperty' relation holds when 'Y is to specify X'.
See one example below:
Problem: X: balance, Y: scale
Solution: IsA
Explanation: Balance is a kind of scale.
Problem: X: include, Y: have
Solution: | Entails |
Given the task definition and input, reply with output. You are given an original reference as well as a system generated reference. Your task is to judge the naturaleness of the system generated reference. If the utterance could have been produced by a native speaker output 1, else output 0.
System Reference: franciscan crab restaurant, is expensively priced and allows kids.
Original Reference: franciscan crab restaurant is in the expensive price range and allows child -s.
| 1 |
Detailed Instructions: We would like you to assess the QUALITY of each of the following argument (discussing Death Penalty) 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 death penalty. An invalid argument is a phrase that cannot be interpreted as an argument or not on the topic of death penalty.
Q: Firstly, many people say that Europe does not have the death penalty so the U.S should not.
A: | Valid |
In this task, you will be presented with the directions of a recipe separated by "," and have to fill in the "___" which is a step that is missing from the recipe.
--------
Question: Clean spinach and pat dry. Toss the garlic with the spinach.,Heat a large frying pan with the olive oil and carefully add the spinach and garlic.,Add the salt and red pepper flakes and toss until lightly wilted.,______,For the Dip:,Place all of the above in a food processor and process until desired consistency.,Serve with your favorite crackers or veggies.
Answer: Remove from the heat and place in a colander over a bowl to drain.
Question: Trim steak and cut into bite sized pieces.,______,Cover and bake for 2 hours at 325°.,Serve over cooked noodles or rice.
Answer: Combine all ingredients.
Question: Pulse everything save for the lamb in a food processor until a paste forms. Rub it all over the leg of lamb, wrap it tightly in plastic, and allow it to marinate overnight.,The next day, remove the lamb from the fridge and wipe excess marinade off.
Place it in a deep roasting pan and allow it to sit out of the fridge for about 45
minutes to bring it up to room temperature.,While it rests, heat your oven to 450° F.,Roast the lamb for 15 minutes, then drop the temperature down to 325° F and roast until a meat thermometer reads 135 to 140°, about 1 to 1 1/2 hours.,______
Answer: | Transfer lamb to a cutting board and tent it with foil. Allow it to rest for 20 minutes
before carving.
|
Detailed Instructions: Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].
Q: ['hi', 'everybody', 'and', 'welcome', 'to', 'lesson', 'six', 'where', "we're", 'going', 'to', 'continue', 'looking', 'at', 'training', 'convolutional', 'neural', 'networks', 'for', 'a', 'computer', 'vision', 'and', 'so', 'we', 'last', 'looked', 'at', 'this', 'so', 'lesson', 'before', 'last', 'and', 'specifically', 'we', 'were', 'looking', 'at', 'how', 'to', 'train', 'an', 'image', 'classifier', 'to', 'pick', 'out', 'breeds', 'of', 'pet', 'one', 'of', '37', 'breeds', 'of', 'pet', 'and', "we've", 'gotten', 'as', 'far', 'as', 'training', 'him', 'at', 'all', 'but', 'we', 'also', 'had', 'to', 'look', 'and', 'figure', 'out', 'what', 'loss', 'function', 'was', 'actually', 'being', 'used', 'so', 'in', 'this', 'model', 'and', 'so', 'we', 'talked', 'about', 'cross-entropy', 'loss', 'which', 'is', 'actually', 'a', 'really', 'important']
A: | ['CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_DIFF', 'DIGIT_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'UNKNOWN_TYPE_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', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF'] |
In this task you are given a tweet and you must identify whether the tweet contains any offense or any form of (untargeted) profanity. Label the post as NOT if the post does not contain offense or profanity. Non-offensive posts do not include any form of offense or profanity. label the post as OFFENSIVE if the post contains offensive language or a targeted (veiled or direct) offense. Twitter user mentions were substituted by @USER and URLs have been substitute by URL.
[EX Q]: @USER I’m done with you as well. An INTENTIONAL 11th hour attack completely based on hearsay and you want an investigation? What do you think they’ll find other than he said she said. Feinstein admitted she sat on this and here you are ready to lockstep with the swamp.
[EX A]: NOT
[EX Q]: @USER They are hoping all over it. But then they are probably the biggest crowd of racist bigots in the country they back antifa
[EX A]: OFFENSIVE
[EX Q]: @USER @USER @USER So ist es! #TheDeepState #Jesuiten #Cabal #satanists #NWO #KalergiPlan ~ #KalergiPreis #WhiteGenocide #COMMUNISM #Antifa #AlbertPike1871 ‼️ #DrainTheSwamp #LockThemAllUp #Guantanamo #EXPROPRIATE #QAnon 🐇🕳️ @USER @USER @USER #POTUS45 #Trump2020
[EX A]: | NOT
|
Detailed Instructions: In medical studies, treatments are tested within a group of study participants. To determine if a new treatment works, various outcomes are measured in the people who take part in the study. You will be given a sentence of a study report in which your task is to list the phrases that give information about the outcomes of the study. You should list the phrases in the same order that they appear in the text, separated by commas. If no information about the outcome is mentioned, just answer with: "not found".
Outcomes contain: outcomes measured in patients: like blood sugar,
outcomes regarding the intervention: like effectiveness, costs
the score on a medical test or questionnaire,
positive or negative events in the patient groups: like quitting smoking, or adverse reactions.
Do not mention numbers or results, interpretations of outcomes, outcome mentions without relevant information.
See one example below:
Problem: Effects of 12 weeks' treatment with a proton pump inhibitor on insulin secretion, glucose metabolism and markers of cardiovascular risk in patients with type 2 diabetes
Solution: insulin secretion, glucose metabolism and markers of cardiovascular risk
Explanation: The study is measuring effects of a treatment on several outcomes, which are: insulin secretion, glucose metabolism and markers of cardiovascular risk.
Problem: No statistically significant differences in myocardial perfusion measured were found with xenon-133 in this small group between rest and dipyridamole load for ionic and non-ionic contrast media .
Solution: | myocardial perfusion |
In this task, you are given two strings A,B. Find the longer of the two lists, convert it to lowercase, and return all the unique alphabets used in it. The two input strings are never equal.
[Q]: PWGyZjshniwSVo, JQAYIjshniwSuhAkF
[A]: a, f, h, i, j, k, n, q, s, u, w, y
[Q]: CiLXzsDyDZkLqb, hYDyDZkLtfYos
[A]: b, c, d, i, k, l, q, s, x, y, z
[Q]: FVogDZnngnKMunth, FACDZnngnKHrYfM
[A]: | d, f, g, h, k, m, n, o, t, u, v, z
|
Given an adjective, generate its antonym. An antonym of a word is a word opposite in meaning to it.
subsonic | supersonic |
You are given a password and you need to generate the number of steps required to convert the given password to a strong password. A password is considered strong if (a) it has at least 6 characters and at most 20 characters; (b) it contains at least one lowercase letter and one uppercase letter, and at least one digit; (c) it does not contain three repeating characters in a row. In one step you can: (1) Insert one character to password, (2) delete one character from password, or (3) replace one character of password with another character.
password = t5un | 2 |
TASK DEFINITION: You are given a country name and you need to return the currency of the given country.
PROBLEM: Sierra Leone
SOLUTION: Sierra Leone Leone
PROBLEM: Lesotho
SOLUTION: Lesotho Loti
PROBLEM: Gabon
SOLUTION: | CFA Franc BEAC
|
Definition: You are given a statement written in Bengali. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement . Output the word from the correct option .
Input: Statement: ২০১৮ সালের ১৫ ডিসেম্বর চলচ্চিত্রটির চিত্রগ্রহণ শুরু হয়। চলচ্চিত্রটির চিত্রগ্রহণ অনুষ্ঠিত হয় <MASK>, রাজবাড়ী, কালিয়াকৈর ও পুরান ঢাকায়। কাহিনীর বিশ্বাসযোগ্যতা ধরে রাখার নিমিত্তে দৌলতদিয়ার যৌনপল্লিতে শুটিং করা হয়েছে। ২০১৯ সালের ১৫ জানুয়ারি চলচ্চিত্রটির চিত্রগ্রহণ শেষ হয়।
Option A: কালিয়াকৈর
Option B: মানিকগঞ্জ
Option C: রাজবাড়ী
Option D: মক্কা
Output: | মানিকগঞ্জ |
Given the task definition and input, reply with output. In this task you will be given a list, of lists, of integers. For every inner list contained in the input list, you should multiply every even number in that list. The output should be a list of integers with the same length as the number of lists in the input list. If there are no even numbers in an inner list you should output 0 for that list.
[[-45, 25, 33, -29, -30], [-38, 10], [35, 14, 28]]
| [-30, -380, 392] |
In this task you are given a passage in Bulgarian as the input content. You are expected to generate a suitable title for the passage which accurately summarizes the contents of the passage. The input is provided in the form of a long passage comprising of multiple sentences. The output should be restricted to a maximum of 20 words which describe the passage and its contents. The output can include words from the passage.
Example Input: Content:Доналд Туск се тагна във фейсбук от България. Председателят на Европейския съвет пристигна у нас по покана на президента Румен Радев.Двамата ще се срещнат утре по обяд. След края на разговорите са предвидени и изказвания пред медии. Преди да пристигне в София, Туск беше на посещение в Македония.Във фейсбук тази вечер Доналд Туск не пропусна да изкаже съболезнования и за трагедията в Русия. Ужасна новина. Мислите ни са с близките на жертите и ранените, написа той в социалната мрежа.
Example Output: Доналд Туск пристигна в България (СНИМКА)
Example Input: Content:Маркус Гюнтхарт защити решението си да предложи „уайлд кард“ на Мария Шарапова за предстоящия тенис турнир от сериите Premier в Щутгарт. Поканата към рускинята разбуни духовете в тенис средите, като огромна част от колежките на Шарапова възроптаха срещу факта, че тя ще направи завръщането си на корта в Щутгарт на 26 април, когато изтича наказанието ѝ за употреба на мелдоний. „Арбитражният спортен съд прецени, че тя по-скоро е направила грешка, отколкото да е взимала допинг съзнателно. Също така тя публично обяви случилото се още преди официалното разкритие и си пое последствията, а да не забравяме и че си изтърпя наказанието“, каза директорът на надпреварата Гюнтхарт в интервю за вестник „Зюддойче Цайтунг“…. Източник на топ новината: : Гюнтхарт: Шарапова си изстрада последствията
Example Output: Гюнтхарт: Шарапова си изстрада последствията
Example Input: Content:Снимка: Информационна агенция Фокус Асеновград. Община Асеновград прекрати участието си във Фонда за развитие на летище „Пловдив“. Решението е било взето на днешното заседание на Общинския съвет, като за него са гласували 22, 6 са били „против“ и трима са се въздържали. Това съобщиха за Радио „Фокус”-Пловдив от Общината. Община Асеновград, която е съучредител на фонда, отчита, че вече шест години няма преки инвестиционни ползи за развитието на местния туризъм и бизнес. Предложението бе внесено за разглеждане в Общинския съвет от кмета Емил Караиванов. Цветана ТОНЧЕВА © 2017 Всички права запазени. Позоваването на Информационна агенция Фокус е задължително!
Example Output: | Община Асеновград прекрати участието си във Фонда за развитие на летище „Пловдив“
|
The input contains texts obtained from news articles, ted talks, movie transcripts, radio transcripts, science and technology texts, and other short articles curated from the web and professional translators. Your task is to translate the given Yoruba sentence into the English language. Please bear in mind the following guidelines while doing the translation: 1) Generated output should be natural language and formal form of each sentence in your language. The output sentence should not be a colloquial form of the input sentence. The generated output should be in natural language 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) Numbers and fully capitalized words like SEPTEMBER, or 10 HOURS *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. 5) Note the input is in sentence case except for special placeholders. Please do the same in your translations.
Èdè Adití Lọ́nà ti Rùwáńdà ni wọ́n fi ṣe ilé ẹ̀kọ́ náà, ìyẹn sì ni àkọ́kọ́ irú ẹ̀. Àwọn mẹ́tàlélógún (23) ló wá sílé ẹ̀kọ́ náà, wọ́n sì kọ́ bí wọ́n ṣe lè túbọ̀ mọ̀ọ̀yàn kọ́, pàápàá bí wọ́n ṣe lè kọ́ àwọn adití lẹ́kọ̀ọ́ Bíbélì, títí kan àwọn tí kò fi bẹ́ẹ̀ gbọ́rọ̀.
The class, which was made up of 23 students, learned how to become more effective when teaching deaf and hard-of-hearing individuals about the Bible.
Eṣinṣín ń pọntí; ekòló ń ṣú ọ̀lẹ̀lẹ̀; kantí-kantí ní ká wá nǹkan dí agbè lẹ́nu kí nǹkankan má kòó sí i.
The fly is procuring wine while the worm is cooking bean-meal, and the sugar-fly asks them to find something to cork the gourd so nothing would enter into it.
Ẹ̀ka ọ́fíìsì wa ní Japan ròyìn pé kò sí akéde kankan tó kú, àmọ́ méje lára àwọn ará wa fara pa.
| The Japan branch office reports that no publishers were killed but seven of our brothers and sisters suffered injuries.
|
Given a pair of words, deduce the type of relationship between them. The various types of relations are: 'Entails, HasProperty, Synonym, Antonym, HasA, MemberOf, PartOf, MadeOf, IsA'. Let's denote the first word by X and the second word by Y. An 'IsA' relation holds when 'X is a kind of Y'. An 'Antonym' relation holds when 'X can be used as the opposite of Y'. A 'Synonym' relation applies when 'X can be used in place of Y, without changing the meaning'. A 'PartOf' relation holds when 'X is a part of Y'. A 'MemberOf' relation holds when 'X is a member of Y'. A 'MadeOf' relation holds when 'X is made of Y'. An 'Entailment' relation holds when 'If X is true, then Y is true as well'. A 'HasA' relation holds when 'X can have or contain Y'. A 'HasProperty' relation holds when 'Y is to specify X'.
Example: X: balance, Y: scale
Example solution: IsA
Example explanation: Balance is a kind of scale.
Problem: X: animal, Y: baby
| Solution: HasA |
Given a part of privacy policy text, identify the type of personal information which is collected, used, tracked or retained. The type of information should be present inside the given policy text, answer as 'Not Specified' otherwise
Ex Input:
The site collects your user profile for an additional (non-basic) service or feature. Collection happens when you explicitly provide information in an unspecified way.
Ex Output:
User profile
Ex Input:
The site collects your website activities for analytics or research. Collection happens on the website, and your data is aggregated or anonymized.
Ex Output:
User online activities
Ex Input:
The site collects your website activities for personalization or customization. Collection happens when you implicitly provide information on the website, and your data is aggregated or anonymized. You can configure your privacy with browser settings for the collection of your information.
Ex Output:
| User online activities
|
Subsets and Splits