prompt
stringlengths 47
13.4k
| response
stringlengths 0
2.99k
|
|---|---|
Definition: In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to classify the command into one of these seven categories: (1) majority, (2) unique, (3) superlative, (4) count, (5) comparative, (6) aggregation, and (7) ordinal.
Here are the defications of each category:
1. majority: Describing the majority values (most or all) over one column, with the scope of all table rows or a subset of rows
2. unique: Describing one unique row, regarding one column, with the scope of all table rows or a subset of rows
3. Superlative: Describing the maximum or minimum value in a column, with the scope of all table rows or a subset of rows
4. Ordinal: Describing the n-th maximum or minimum value in a column, with the scope of all table rows or a subset of rows
5. Comparative: Comparing two rows in the table, regarding their values in one column
6. Count: counting some rows in the table based on the values in one column, with the scope of all table rows or a subset of rows
7. Aggregation: Describing the sum or average value over a column, with the scope of all table rows or a subset of rows.
Here are the definitions of logical operators for understanding of command:
1. count: returns the number of rows in the view.
2. only: returns whether there is exactly one row in the view.
3. hop: returns the value under the header column of the row.
4. and: returns the boolean operation result of two arguments.
5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column.
6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column.
7. argmax/argmin: returns the row with the max/min value in header column.
8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column.
9. eq/not_eq: returns if the two arguments are equal.
10. round_eq: returns if the two arguments are roughly equal under certain tolerance.
11. greater/less: returns if the first argument is greater/less than the second argument.
12. diff: returns the difference between two arguments.
13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument.
14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument.
15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument.
16. filter_all: returns the view itself for the case of describing the whole table
17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument.
18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument.
19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument.
20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument.
21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument.
22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.
Input: round_eq { avg { all_rows ; silver } ; 5.2 }
Output: | aggregation |
Which movie is the following review about?
The Best of Youth more than earns its running time. | best of youth |
In this task, you need to output 'Yes' if the given number is a prime number otherwise output 'No'. A 'prime number' is a a whole number above 1 that can not be made by multiplying other whole numbers.
Example Input: 64195
Example Output: No
Example Input: 4501
Example Output: No
Example Input: 17293
Example Output: | Yes
|
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.
--------
Question: [-96.159 8.717 9.581 6.353 -9.328 -98.23 ]
Answer: -98.23
Question: [-96.178 10.114 29.296]
Answer: -96.178
Question: [39.24 -0.907]
Answer: | 39.24
|
You will be given a definition of a task first, then some input of the task.
Given an input word generate a word that rhymes exactly with the input word. If not rhyme is found return "No"
strange
Output: | change |
In this task, you are given two sets, and a question. You need to find whether an element is at the intersection of two given sets. A Set is shown by two curly braces and comma-separated numbers inside, like {1, 2, 3}. The intersection of two given sets is the largest set which contains all the elements that are common to both sets. An element is at the intersection of two given sets, A and B, if common to both A and B. Classify your answers into 'Yes' or 'No'.
Set1: '{11}', Set2: '{11, 12, 5, 6}'. Is the element '11' in the intersection of Set1 and Set2 ?
Yes
Set1: '{4, 6, 8, 9, 11, 12, 14, 15, 16, 18}', Set2: '{3, 4, 8, 9, 11, 13, 14, 20}'. Is the element '4' in the intersection of Set1 and Set2 ?
Yes
Set1: '{1, 2, 3, 4, 8, 11, 13, 15, 16, 18}', Set2: '{8, 6}'. Is the element '15' in the intersection of Set1 and Set2 ?
| No
|
Instructions: Given a sentence in the Japanese and Thai language. Your task is check if the Filipino sentence is translation of Japanese. if the translation is correct than generate label "Yes", otherwise generate label "No".
Input: Japanese: それには、前オーストラリア首相のジョン・ハワードやワールド・ワイド・ウェブの発明者、ティム・バーナーズ-リー卿を含む数人の国際的な有名人だけでなく政治やエンターテイメントの世界からの主要な人物が参加するということだ。
Thai: พิธีนี้คาดว่าจะมีบุคคลสำคัญจากทั่วโลกทั้งด้านการเมืองและการบันเทิงตลอดจนผู้นำสากลหลายท่านซึ่งรวมถึงอดีตนายกรัฐมนตรี จอห์น โฮเวิร์ดของออสเตรเลีย รวมถึงผู้คิดค้นและประดิษฐ์ เวิลด์ไวด์เว็บ เซอร์ทิม เบอร์เนิร์ส-ลี จะเข้าร่วมงานด้วย
Output: | Yes |
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.
Q: SeNOgGRY
A: | SNgGRY |
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.
Ex Input:
[-12.915 -57.044 86.691]
Ex Output:
86.691
Ex Input:
[ 68.67 -77.595 -41.146]
Ex Output:
-77.595
Ex Input:
[ 65.606 -12.674 -91.107 73.209 77.862 -29.268]
Ex Output:
| -91.107
|
In this task you will be given a list of integers. You should remove all of the integers that are divisible by 3 from the list. If every integer in the input list is divisible by 3 then an empty list should be returned. Zero is divisible by 3.
Q: [16, -10, 81, 1, 18, 65, 1, 37, -43, -53]
A: | [16, -10, 1, 65, 1, 37, -43, -53] |
In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the alphabetical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no alphabetical element is in the list.
Q: ['3195', '8693', 'J', 'A', '1903', '1665', '1879', 'b', 'O', 'g', '2639', '5377', 'W', 'i', 'm', '1087', 'K', '3847', 'F', 'I', '4527', '247', 'Y', '4689']
A: 3, 4, 8, 9, 10, 13, 14, 15, 17, 19, 20, 23
****
Q: ['8643', '6883', '5675', 'm', '1439', 'O']
A: 4, 6
****
Q: ['x', '3483', 'x', 'H', '8049', 'r', 't', '7915', 'X', 'W', 'A', '4471', 'r', '6313', '8725', 'l', 'd', '3017', '7309', '5451', '8161', '285']
A: | 1, 3, 4, 6, 7, 9, 10, 11, 13, 16, 17
****
|
In this task, you will be given a list of numbers. The goal is to divide all the numbers in the list by a constant such that the sum of the resulting list is 1. The output should be rounded to 3 decimals.
Ex Input:
[9.319, -75.878, 107.472, 9.37, 94.991, 101.315, -15.634, -54.696, -68.741, 185.382]
Ex Output:
[ 0.032 -0.259 0.367 0.032 0.324 0.346 -0.053 -0.187 -0.235 0.633]
Ex Input:
[31.541, -32.498, 202.96]
Ex Output:
[ 0.156 -0.161 1.005]
Ex Input:
[140.565, 187.293, 62.554, 179.917, 97.368, 106.263, 248.46]
Ex Output:
| [0.137 0.183 0.061 0.176 0.095 0.104 0.243]
|
Q: The input is taken from a negotiation between two participants who take the role of campsite neighbors and negotiate for Food, Water, and Firewood packages, based on their individual preferences and requirements. Given an utterance and recent dialogue context containing past 3 utterances (wherever available), output Yes if the utterance contains the self-need strategy, otherwise output No. self-need is a selfish negotiation strategy. It is used to create a personal need for an item in the negotiation, such as by pointing out that the participant sweats a lot to show preference towards water packages.
Context:
Utterance: 'Hi! I'm really hoping to get a lot of water. I love outdoor activities like hiking and kayaking so I'll need to stay hydrated on the trip.'
A: | Yes |
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].
Ex Input:
It's funny how his entire comment just gets destroyed by one link in response to it that isn't addressed at all.
Ex Output:
no
Ex Input:
Just be honest and up front about it, but don't be rude. Just say hey that ain't my thing, and if he respects that then carry on with whatever you're both comfortable with. But if he doesn't respect it and keeps going he's most likely both a bit odd, and not really a keeper. I could go either way to be honest, it's not my favorite thing but hey if someone's into that who am I to judge
Ex Output:
no
Ex Input:
**WE LIVE IN A SOCIETY**
Ex Output:
| no
|
Detailed Instructions: Given news headlines and an edited word. The original sentence has word within given format {word}. Create new headlines by replacing {word} in the original sentence with edit word. Classify news headlines into "Funny" and "Not Funny" that have been modified by humans using an edit word to make them funny.
See one example below:
Problem: News Headline: France is ‘ hunting down its citizens who joined {Isis} without trial in Iraq
Edit: twins
Solution: Not Funny
Explanation: The edited sentence is not making much sense, therefore it's not funny.
Problem: News Headline: North Korea accuses US of ' criminal moves ' as three Navy {carriers} operate in Asian waters
Edit: dancers
Solution: | Funny |
In this task you will be given two lists of numbers and you need to calculate the intersection between these two lists. The intersection between two lists is another list where every element is common between the two original lists. If there are no elements in the intersection, answer with an empty list. Your list of numbers must be inside brackets. Sort the numbers in your answer in an ascending order, that is, no matter what the order of the numbers in the lists is, you should put them in your answer in an ascending order.
Let me give you an example: [2,5,1,4],[2,5,8,4,2,0]
The answer to this example can be: [2,4,5]
Here is why: The elements 2,4, and 5 are in both lists. This is a good example.
OK. solve this:
[5, 1, 7, 10, 8, 9] , [6, 7, 4, 2, 5, 4]
Answer: | [5, 7] |
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'.
Spiritualiteit en zelfontplooiing ' heeft zich dikwijls manmoedig moeten inhouden . | None |
Instructions: 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: You can make no specified choices about the use of generic personal information by the site, which uses it for advertising.
Output: | Generic personal information |
Detailed Instructions: In this task you will be given a list of numbers and you need to find the mean (average) of that list. The mean of a list can be found by summing every number in the list then dividing the result by the size of that list. The output should be rounded to 3 decimal places.
Problem:[226.383, 37.978, 174.444, 117.212]
Solution: | 139.004 |
Given the task definition and input, reply with output. Given a concept word, generate a hypernym for it. A hypernym is a superordinate, i.e. a word with a broad meaning constituting a category, that generalizes another word. For example, color is a hypernym of red.
market
| industry |
Instructions: You are asked to create a question containing a blank (_), based on the given context word. Your question must contain two related but different objects; for example "trophy" and "suitcase". The expected answer to your question must be one of the objects present in the sentence. The expected answer must not be associated with any specific word in the question; instead it should depend on the context present in the question. The expected answer should not be equally likely to fill the blank. For your question, there should be a agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals or proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style, pattern or phrases in each question, try to increase diversity by varying sentence structure, blank placement etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Object X and Y have the same number e.g. when ObjectX is singular, Object Y must be singular, too. The two objects (Object X & Object Y) should be used ONCE in your question. Here is a list of attributes and associated pair of contrastive words which may be used to create a valid question using the objects. You can use either of the contrastive words, but not both. You should think about more such attributes and associated words and use them in your question.
| Attribute | triggerword | contrastive triggerword |
| age | old | new |
| altitude | low | high |
| area | small | vast |
| brightness | dark | light |
| clarity | obscure | clear |
| cleanness | dirty | clean |
| complexity | simple | complex |
| cost | cheap | expensive |
| density | sparse | dense |
| depth | shallow | deep |
| distance | near | far |
| electric conductivity | low | high |
| flexibility | rigid | flexible |
| granularity | fine | coarse |
| hardness | soft | hard |
| length | short | long |
| magnitude | small | large |
| mass | small | large |
| odor | weak | strong |
| pressure | low | high |
| resistance | low | high |
| shape | round | sharp |
| shape | flat | spiky |
| size | small | large |
| sound | quiet | loud |
| sound pitch | low | high |
| speed | slow | fast |
| stability | unstable | stable |
| strength | weak | strong |
| temperature | low | high |
| texture | smooth | rough |
| thermal conductivity | low | high |
| thickness | thin | thick |
| volume | small | large |
| weight | light | heavy |
| width | narrow | wide |
| location | in | out |
| location | up | down |
| location | above | below |
| location | on | off |
| location | to | from |
Input: Context Word: hard drive.
Output: | He bought an external hard drive of the same capacity of his dying PC and transferred files until the _ is empty. |
Given the task definition, example input & output, solve the new input case.
We would like you to assess the QUALITY of each of the following argument (discussing Gun Control) and determine if the argument is Valid or Invalid. A valid argument is clearly interpretable and either expresses an argument, or a premise or a conclusion that can be used in an argument for the topic of gun control. An invalid argument is a phrase that cannot be interpreted as an argument or not on the topic of gun control.
Example: If gun bans worked there would be no gun deaths in the countries that have banned guns.
Output: Valid
It is an argument that claims that gun bans will not work.
New input case for you: Mine are rights, theirs are crimes and a man in the right is justified in using deadly force to protect his life and rights.
Output: | Valid |
In this task you are given a list of numbers and you need to find the average of each two consecutive values. The average of two numbers a and b is calculated as: (a + b) /2. The output should be a list of the averages of each two consecutive values. A list is presented with two brackets and comma-separated values, like: [1,2,3].
[Q]: [60, 91, 22, -94, -97, -3, -34, -62, -88, -42, 22, -93, -33, -19]
[A]: [75.5, 56.5, -36.0, -95.5, -50.0, -18.5, -48.0, -75.0, -65.0, -10.0, -35.5, -63.0, -26.0]
[Q]: [-8, -54, 31, -40, 58, -2, 45, -86, -62, -14, 94]
[A]: [-31.0, -11.5, -4.5, 9.0, 28.0, 21.5, -20.5, -74.0, -38.0, 40.0]
[Q]: [-83, -61, 67, 27, 22, 69, -59, 81, -42, 99, -13, -23, 49, -27]
[A]: | [-72.0, 3.0, 47.0, 24.5, 45.5, 5.0, 11.0, 19.5, 28.5, 43.0, -18.0, 13.0, 11.0]
|
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.
--------
Question: Carol Townsend: But , I think that 's too daring for words ! I 'd like to try _ one _ .
Eric: Oh , Carol !
Carol Townsend: Yes , Eric , just one . Do give me one , Charlotte .
Charlotte: Well , I , eh , I just used up the last box , I 'm sorry .
Eric: I 'm glad of that . I do not approve of women smoking cigars .
Carol Townsend: Eric is so old fashioned - about some things . Ha - ha . Well , I suppose I 've got to go back to plain , everyday , cigarettes .
Answer: OTHER
Question: Michel Dorn: We just celebrated Detective McConnell 's 30th birthday . He was _ three _ in 1987 . Same age as your twins .
Miles Lennon: Yeah , well , at least he got to be 30 .
Answer: AGE
Question: Jennifer Jareau: What 's up , Spence ?
Dr. Spencer Reid: There 's something strange about this one branch of the family tree . Garcia ?
Penelope Garcia: Talk to me . I am fluent in genius .
Dr. Spencer Reid: Roy and Becky Danary . They died in _ 1985 _ , leaving behind a son named William Danary , but there 's no record of what happened to him .
Penelope Garcia: The Danarys were Peace Corps workers in Ecuador . They died in a car accident there ... and you 're right , their kid just sort of vanished . Let me do some digging , and I will call you back .
Answer: | YEAR
|
The given sentence contains a typo which could be one of the following four types: (1) swapped letters of a word e.g. 'niec' is a typo of the word 'nice'. (2) missing letter in a word e.g. 'nic' is a typo of the word 'nice'. (3) extra letter in a word e.g. 'nicce' is a typo of the word 'nice'. (4) replaced letter in a word e.g 'nicr' is a typo of the word 'nice'. You need to identify the typo in the given sentence. To do this, answer with the word containing the typo.
Two tdedy bears sitting beside each other in a chair. | tdedy |
Detailed Instructions: 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
Q: { 13} we have considered the issue raised in this case on numerous occasions.
A: | non-overruling |
Teacher: You are asked to create a question containing a blank (_), based on the given context word. Your question must contain two related but different objects; for example "trophy" and "suitcase". The expected answer to your question must be one of the objects present in the sentence. The expected answer must not be associated with any specific word in the question; instead it should depend on the context present in the question. The expected answer should not be equally likely to fill the blank. For your question, there should be a agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals or proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style, pattern or phrases in each question, try to increase diversity by varying sentence structure, blank placement etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Object X and Y have the same number e.g. when ObjectX is singular, Object Y must be singular, too. The two objects (Object X & Object Y) should be used ONCE in your question. Here is a list of attributes and associated pair of contrastive words which may be used to create a valid question using the objects. You can use either of the contrastive words, but not both. You should think about more such attributes and associated words and use them in your question.
| Attribute | triggerword | contrastive triggerword |
| age | old | new |
| altitude | low | high |
| area | small | vast |
| brightness | dark | light |
| clarity | obscure | clear |
| cleanness | dirty | clean |
| complexity | simple | complex |
| cost | cheap | expensive |
| density | sparse | dense |
| depth | shallow | deep |
| distance | near | far |
| electric conductivity | low | high |
| flexibility | rigid | flexible |
| granularity | fine | coarse |
| hardness | soft | hard |
| length | short | long |
| magnitude | small | large |
| mass | small | large |
| odor | weak | strong |
| pressure | low | high |
| resistance | low | high |
| shape | round | sharp |
| shape | flat | spiky |
| size | small | large |
| sound | quiet | loud |
| sound pitch | low | high |
| speed | slow | fast |
| stability | unstable | stable |
| strength | weak | strong |
| temperature | low | high |
| texture | smooth | rough |
| thermal conductivity | low | high |
| thickness | thin | thick |
| volume | small | large |
| weight | light | heavy |
| width | narrow | wide |
| location | in | out |
| location | up | down |
| location | above | below |
| location | on | off |
| location | to | from |
Teacher: Now, understand the problem? If you are still confused, see the following example:
Context word: fit.
Solution: The trophy doesn't fit into the brown suitcase because _ is too large.
Reason: The question is about two related but different objects (i) "trophy" and (ii) "suitcase". The quesion contains exactly one blank (_). The expected answer is "trophy" which is one of the objects.
Now, solve this instance: Context Word: dodgeball.
Student: | At the dodgeball tournament, the concessions stand didn't serve pretzels, but had chips, because the players seemed to abhor the _ more. |
Definition: In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to classify the command into one of these seven categories: (1) majority, (2) unique, (3) superlative, (4) count, (5) comparative, (6) aggregation, and (7) ordinal.
Here are the defications of each category:
1. majority: Describing the majority values (most or all) over one column, with the scope of all table rows or a subset of rows
2. unique: Describing one unique row, regarding one column, with the scope of all table rows or a subset of rows
3. Superlative: Describing the maximum or minimum value in a column, with the scope of all table rows or a subset of rows
4. Ordinal: Describing the n-th maximum or minimum value in a column, with the scope of all table rows or a subset of rows
5. Comparative: Comparing two rows in the table, regarding their values in one column
6. Count: counting some rows in the table based on the values in one column, with the scope of all table rows or a subset of rows
7. Aggregation: Describing the sum or average value over a column, with the scope of all table rows or a subset of rows.
Here are the definitions of logical operators for understanding of command:
1. count: returns the number of rows in the view.
2. only: returns whether there is exactly one row in the view.
3. hop: returns the value under the header column of the row.
4. and: returns the boolean operation result of two arguments.
5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column.
6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column.
7. argmax/argmin: returns the row with the max/min value in header column.
8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column.
9. eq/not_eq: returns if the two arguments are equal.
10. round_eq: returns if the two arguments are roughly equal under certain tolerance.
11. greater/less: returns if the first argument is greater/less than the second argument.
12. diff: returns the difference between two arguments.
13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument.
14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument.
15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument.
16. filter_all: returns the view itself for the case of describing the whole table
17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument.
18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument.
19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument.
20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument.
21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument.
22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.
Input: round_eq { avg { all_rows ; attendance } ; 33151 }
Output: | aggregation |
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.
Concept: gorilla, Relatum: foot. | mero |
Detailed Instructions: In this task you will be given an arithmetic operation in Italian and you have to find its answer. The operations 'addition' and 'subtraction' have been replaced with their italian translations i.e you need to perform addition when you see 'aggiunta' and subtraction in case of 'sottrazione'.
Problem:6916 aggiunta 5100 aggiunta 6186 aggiunta 8073 sottrazione 2144 aggiunta 3226 sottrazione 4012 sottrazione 9880
Solution: | 13465 |
In this task you are given a list of numbers and you need to find the average of each two consecutive values. The average of two numbers a and b is calculated as: (a + b) /2. The output should be a list of the averages of each two consecutive values. A list is presented with two brackets and comma-separated values, like: [1,2,3].
[99, 29, 62, 55, -61, 21, 91, 93, -41, 72, -95, -28, -34, 46, -8] | [64.0, 45.5, 58.5, -3.0, -20.0, 56.0, 92.0, 26.0, 15.5, -11.5, -61.5, -31.0, 6.0, 19.0] |
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 website activities for service operations or security. Collection happens when you implicitly provide information on the website.
Ex Output:
User online activities
Ex Input:
The site collects your contact information for advertising. Collection happens in an unspecified way. You can choose not to use the service or feature for the use of your information.
Ex Output:
Contact
Ex Input:
You can make a choice about your privacy not described by our label scheme the use of cookies and tracking elements by a third party, which collects or receives it for analytics or research.
Ex Output:
| Cookies and tracking elements
|
Given the task definition and input, reply with output. In this task, you will be given a list of numbers. The goal is to divide all the numbers in the list by a constant such that the sum of the resulting list is 1. The output should be rounded to 3 decimals.
[177.14, -0.78, -16.492]
| [ 1.108 -0.005 -0.103] |
Given news headlines and an edited word. The original sentence has word within given format {word}. Create new headlines by replacing {word} in the original sentence with edit word. Classify news headlines into "Funny" and "Not Funny" that have been modified by humans using an edit word to make them funny.
Q: News Headline: {Greg Gianforte} ' not sure ' he would have sent Trump CNN body-slam tweet
Edit: Wrestler
A: Funny
****
Q: News Headline: Questions about Trump overwhelm Republican Sen. Chuck Grassley 's {event} in Iowa
Edit: party
A: Not Funny
****
Q: News Headline: South Korea Court Approves {Arrest} of Samsung Heir Jay Y. Lee
Edit: burial
A: | Not Funny
****
|
Detailed Instructions: 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.
Problem:[[-30, -6, -6, 29, 30], [-32, -6, -8, 50, 23], [41, -28, -31], [6, 27], [31, -16, -28, 12, -15], [16, -21], [-3, 49, -34, 38, -27]]
Solution: | [-32400, -76800, -28, 6, 5376, 16, -1292] |
Given the task definition and input, reply with output. 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.
Kò sí ará wa kankan tó fara pa tàbí tó kú nínú ìṣẹ̀lẹ̀ náà.
| None of our brothers and sisters were injured or killed. |
In this task you will be given a list of integers. You should find the minimum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one integer subtracted by another. The output should be a single integer which is the smallest possible absolute distance.
Q: [85, 77, 73, 4, -6, 93]
A: 4
****
Q: [-27, 96, -37, 39, 15]
A: 10
****
Q: [34, 10, 6, 69, -12, -6, 7, -99]
A: | 1
****
|
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.
Input: Consider Input: [-40.716 76.732 -81.067 51.003 58.293 -47.244]
Output: -81.067
Input: Consider Input: [-32.571 -72.569 -21.998 12.985 82.911 21.548 11.558 86.122 14.454
74.508]
Output: 86.122
Input: Consider Input: [-63.815 74.559 -40.608]
| Output: 74.559
|
In this task you are expected to write an SQL query that will return the data asked for in the question. An SQL query works by selecting data from a table where certain conditions apply. A table contains columns where every row in that table must have a value for each column. Every table has a primary key that uniquely identifies each row, usually an id. To choose which columns are returned you specify that after the "SELECT" statement. Next, you use a "FROM" statement to specify what tables you want to select the data from. When you specify a table you can rename it with the "AS" statement. You can reference that table by whatever name follows the "AS" statement. If you want to select data from multiple tables you need to use the "JOIN" statement. This will join the tables together by pairing a row in one table with every row in the other table (Cartesian Product). To limit the number of rows returned you should use the "ON" statement. This will only return rows where the condition specified after the statement is true, this is usually an equals operator with primary keys. You can also use the "WHERE" statement to specify that only rows with column values statisfying a certain condition, should be returned. The "GROUP BY" statement will group rows together that have equal column values for whatever columns follows the statement. The "HAVING" statement will return groups that statisfy whatever condition follows the statement. Any column(s) being returned from grouped rows must either be an aggregate function, (AVG, MAX, COUNT, SUM, ...) of a column, or the column(s) that the data was grouped by. To sort the returned data you can use the "ORDER BY" command which will order the data by whatever aggregate function or column follows the statement. The "DESC" statement will sort in descending order and the "ASC" statement will sort in ascending order. Finally, you can use the "LIMIT" statement to return a certain number of rows. When "*" is used in an SQL statement every column is returned. For example, SELECT * FROM table WHERE attribute = 1, will select every column from rows with the attribute column equal to 1.
Q: What are the ids of stations that have latitude above 37.4 and never had bike availability below 7?
A: SELECT id FROM station WHERE lat > 37.4 EXCEPT SELECT station_id FROM status GROUP BY station_id HAVING min(bikes_available) < 7
****
Q: How many documents are with document type code BK for each product id?
A: SELECT count(*) , project_id FROM Documents WHERE document_type_code = "BK" GROUP BY project_id
****
Q: List the wheels and locations of the railways.
A: | SELECT Wheels , LOCATION FROM railway
****
|
Q: 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].
question: who did johannes brahms fell in love with?
A: | #1 return johannes brahms
#2 return who did #1 fell in love with |
Part 1. Definition
You are given first 5 messages from a series of message exchanges between 2 persons playing the game of Diplomacy which is an American strategic board game. You need to generate the next message. The message should be generated such that it fits the context seen so far. Avoid the text that is (i) tangent to the context, (ii) repeats the context.
Part 2. Example
['Heyyyy Turkey', 'Whatcha thinking re: start of the game?', "It kind of depends. I'll probably want to stop Russia from advancing south", "I'm kind of afraid of Austria and Russia teaming together on me", 'I mean if that happens you’re donezos']
Answer: What vibes are you getting from each of them?
Explanation: The message fits the context as it asks for the vibes of 2 of them which refers to 2 countries: Austria and Russia in the second last message. Thus it is a positive example.
Part 3. Exercise
['Have you talked to England yet? I got an interesting message from them.', 'yeah, he wants to do a western triple. what do you think?', "I'm in", "What do we do from here, I want to make sure we don't let everyone else in on our scheme yet but I also don't want to upset you", 'I think we need to talk about how to split up bel hol and den']
Answer: | I think I should get hol you bel and England den |
In this task, you are given a country name and you need to return the Top Level Domain (TLD) of the given country. The TLD is the part that follows immediately after the "dot" symbol in a website's address. The output, TLD is represented by a ".", followed by the domain.
Example: Andorra
Example solution: .ad
Example explanation: .ad is the TLD of the country called Andorra.
Problem: Pitcairn Islands
| Solution: .pn |
Instructions: 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.
Input: customer: Hi,I am Jerry Jones.
agent: Hello, how can I assist you today?
customer: I need a connecting flight to Washington. As, I am a journalist I want to collect some data from library of congress. Can you help me to book a flight with the price of 500?
agent: Sure, Can you share me your trip dates please?
customer: I want to fly on 08/08 and return on 08/10.
agent: May I know your journey locations?
customer: My source is from PHL and destination is at IAD.
agent: Ok, wait for some time.
__
agent: There is a Jetblue airline with single connection under fare of 100. Shall I proceed for booking with airline number 1009?
customer: Please proceed with the booking.
agent: Your ticket has been confirmed.
customer: Thanks for your awesome service.
agent: Thanks for connecting us.
Output: | customer: Sure. |
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.
Q: I Wish I Had Some Cheese
A: | i wish i have some cheese oh i want some cheese so please cheese be very special to me so please i want some cheese |
Given the task definition and input, reply with output. 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.
So I argue that 3000 years of use does provide evidence that capital punishment works.
| Valid |
Instructions: 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.
Input: Richard Castle: You know , I was thinking about Gates ' sister , and it got me wondering . Do you have any family I do n't know about ?
Kate Beckett: No , I do n't think so .
Richard Castle: Good . Because this " intimate " wedding of ours ...
Kate Beckett: Oh , no . You , too ?
Richard Castle: How bad is yours ?
Kate Beckett: I 've got over a _ hundred _ .
Richard Castle: I 'm at three hundred over that .
Kate Beckett: Four hundred ?
Richard Castle: Well , to be fair , I am world famous ... ish . I mean , look , it 's a first draft . It just needs some editing . Just brutal , ruthless editing .
Kate Beckett: Castle , Michael Connelly ? You haven't seen him in over a year . And do you not remember what he wrote about your last book ? No . I think we got our first edit .
Richard Castle: Uh , well , I have to invite Connelly , because if he finds out that Jonathan Kellerman made the cut , and I have to invite Kellerman because I have to invite Wes Craven and Stephen King ...
Kate Beckett: Yeah , but we 've got to start somewhere .
Richard Castle: Well , I think I know where . Aunt Theresa ? Really ? After what she posted about me on Facebook ?
Kate Beckett: She took it down .
Output: | OTHER |
Given the task definition and input, reply with output. This task is to find the number of 'For' loops present in the given cpp program.
int main()
{
int count(int x,int y);
int i,j,n,a[100],b[100];
scanf("%d", &n);
for(i=1;i<=n;i++){scanf("%d", &a[i]);}
for(i=1;i<=n;i++){
b[i]=0;
for(j=2;j<=a[i];j++){
b[i]+=count(a[i],j);
}
}
for(i=1;i<=n;i++){printf("%d\n", b[i]);}
return 0;
}
int count(int x,int y)
{
int c=0,k;
if(x==y){c=1;}
if(x%y!=0){c=0;}
if(x!=y&&x%y==0){
for(k=y;k>=2;k--){c+=count((x/y),k);}
}
return(c);
}
| 5 |
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.
Ex Input:
Fact: an organism requires energy for growth.
Topic: organism energy growth.
Ex Output:
Growth is very energy consuming.
Ex Input:
Fact: a warm front causes cloudy and rainy weather.
Topic: warm front rain.
Ex Output:
Behind the warm front are thick, low stratus clouds and possibly more rain.
Ex Input:
Fact: Female gametophytes produce eggs inside the ovaries of flowers.
Topic: gametophytes type.
Ex Output:
| Megaspores develop into female gametophytes.
|
In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the alphabetical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no alphabetical element is in the list.
Q: ['9937', '3305', 'j', 'P', '1633', 'w', '3203', '5707', '9765', '1363', '4165', '8355', '7771', '2535', '1043', '7731', 'O', '1979', '4087', 'G', '9443', 'w']
A: | 3, 4, 6, 17, 20, 22 |
Instructions: Read the given story and classify it as 'imagined', 'recalled', or 'retold'. If a story is imagined, the person who wrote the story is making it up, pretending they experienced it. If a story is recalled, the person who wrote the story really experienced it and is recalling it from memory. If a story is retold, it is a real memory like the 'recalled' stories, but written down much later after previously writing a 'recalled' story about the same events. So, recalled stories and retold stories will be fairly similar, in that they both were real experiences for the writer. Imagined stories have a more linear flow and contain more commonsense knowledge, whereas recalled stories are less connected and contain more specific concrete events. Additionally, higher levels of self reference are found in imagined stories. Between recalled and retold stories, retold stories flow significantly more linearly than recalled stories, and retold stories are significantly higher in scores for cognitive processes and positive tone.
Input: It was six months ago in my home town there was one incident happen in my life. That was my family arrested because of some kind of incident happen in my town. But there was a mistake happen in that incident. Then i investigate about that incident. there are lot of problems happen in my town and the incident also happen in that time. The incident was some one murder in my town. There are some clues identify that shows some of my family members did this. so police arrest my family members. Then I know that my family members don't do this. I investigate about that crime incident. There are lot members involves in that crime. so seriously notice some points about that persons. then I notice there are some aboard members are do this. Then I collect some clues about her. Then I notice every members from that gang. Then I find some clues. Some kind of clues are match with that gang. Then I notice every action of that gang. Then I report to police. They not consider about them. so I find some fingertips of that crime area. I collected the evidence and handover to the police. they seen that and watch that gang seriously. Then one day police notice them. They get some drug and that time police investigate himand they told everything about the crime then my family also release.
Output: | recalled |
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.
Ex Input:
Of the 11 scheduled for the needle in Texas the first part of this year 1 has been on death row for 31 years.
Ex Output:
Valid
Ex Input:
it wouldnt even exist if it werent for the human mind.
Ex Output:
Invalid
Ex Input:
Just because I thought that California is using the chamber as only state.
Ex Output:
| Valid
|
Teacher: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.
Teacher: Now, understand the problem? Solve this instance: Syringotropic hypersensitivity reaction associated with infliximab and leflunomide combination therapy in a child with psoriatic arthritis.
Student: | adverse drug event |
You will be given a definition of a task first, then some input of the task.
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.
Concept: blouse, Relatum: colorful.
Output: | attri |
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 two classes: religious or non-political religious on the topic.
--------
Question: রানুর মতো একটা ভিখারি যেমন পায়ের জুতো অনেক দামি হলেও তাকে কেউ মাথায় তুলে রাখে না তেমন তার মতো একটা ফালতু শিল্পীকে পাপসের মতো পায়ের নিচে রাখায় উচিত
Answer: non-religious
Question: মুসলমানির (দোন কাটানোর) কিছুক্ষন পরের অবস্থা
Answer: non-religious
Question: তৃতীয় বিয়ে নিয়েও সমস্যায় শ্রাবন্তি, এই সংবাদে লুচ্চা ব্যক্তির নিবেদন, আমাকেও একবার সুযোগ দেওয়া হোক
Answer: | non-religious
|
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.
Q: Set1: '{3, 14, 15}', Set2: '{3, 5, 6, 8, 9, 11, 12, 16, 17, 20}'. How many elements are there in the union of Set1 and Set2 ?
A: | 12 |
Given the task definition and input, reply with output. In this task, you are given two sets, and a question. You need to find whether an element is at the intersection of two given sets. A Set is shown by two curly braces and comma-separated numbers inside, like {1, 2, 3}. The intersection of two given sets is the largest set which contains all the elements that are common to both sets. An element is at the intersection of two given sets, A and B, if common to both A and B. Classify your answers into 'Yes' or 'No'.
Set1: '{1, 8, 9, 12, 13, 17, 18}', Set2: '{1, 2, 3, 10, 13, 14, 19}'. Is the element '12' in the intersection of Set1 and Set2 ?
| No |
The given sentence contains a typo which could be one of the following four types: (1) swapped letters of a word e.g. 'niec' is a typo of the word 'nice'. (2) missing letter in a word e.g. 'nic' is a typo of the word 'nice'. (3) extra letter in a word e.g. 'nicce' is a typo of the word 'nice'. (4) replaced letter in a word e.g 'nicr' is a typo of the word 'nice'. You need to identify the typo in the given sentence. To do this, answer with the word containing the typo.
Example Input: Two opeople standing next to a fridge, one writing on it.
Example Output: opeople
Example Input: bus qand a car stopped at a traffic light
Example Output: qand
Example Input: a waer skier is doing a jump and a waterfall
Example Output: | waer
|
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 two classes: religious or non-political religious on the topic.
ভারতের সেনাবাহিনীর ছেলে কডা এবার চাকরি ছেড়ে দেবানি মরেছে চাকরি করতে এসে | non-religious |
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.
See one example below:
Problem: [0,1,0,2,5,1]
Solution: [2,5]
Explanation: The only elements that are not duplicated is 2 and 5. This is a good example.
Problem: [5, 7, 6, 0, 6, 6, 3]
Solution: | [5, 7, 0, 3] |
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.
Given two entities as input, classify as "yes" if second entity is the part of the first entity. Otherwise classify them as "no". These are entities of meronym In linguistics, meronymy is a semantic relation between a meronym denoting a part and a holonym denoting a whole. In simpler terms, a meronym (i.e., second entity) is in a part-of relationship with its holonym (i.e., first entity).
Entity 1: plant
Entity 2: leaf
Solution: yes
Why? The answer is correct. Because the leaf is part of the plant. Therefore, here leaf is meronym and the plant is holonym.
New input: Entity 1: basis
Entity 2: hydrogen and oxygen atom
Solution: | yes |
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'.
--------
Question: zerofiveninezerozerooneeightzerosevensixsevenfive
Answer: 059001807675
Question: fiveeighttwoeightfourfiveeighteightseven
Answer: 582845887
Question: oneseveneightfourseventhree
Answer: | 178473
|
instruction:
In this task, you will be given a list. The list is several integers and letters separated with a comma, written within a []. You can create new lists by dropping one of the items in the input list. Your task is to write a list containing all the possible lists you can make by dropping one item from the input list. For example, if the input list contains two items, you can drop one of the items each time. So the output should be a list comprising two inner lists that you have created by decreasing the items.
question:
['f', 'u', 'r', '6']
answer:
[['f', 'u', 'r'], ['f', 'u', '6'], ['f', 'r', '6'], ['u', 'r', '6']]
question:
['4', 'd', '3', 'A', '0', 'p', 'x']
answer:
[['4', 'd', '3', 'A', '0', 'p'], ['4', 'd', '3', 'A', '0', 'x'], ['4', 'd', '3', 'A', 'p', 'x'], ['4', 'd', '3', '0', 'p', 'x'], ['4', 'd', 'A', '0', 'p', 'x'], ['4', '3', 'A', '0', 'p', 'x'], ['d', '3', 'A', '0', 'p', 'x']]
question:
['c', 't', 'm', '8', 'T', 'r', 'm']
answer:
| [['c', 't', 'm', '8', 'T', 'r'], ['c', 't', 'm', '8', 'T', 'm'], ['c', 't', 'm', '8', 'r', 'm'], ['c', 't', 'm', 'T', 'r', 'm'], ['c', 't', '8', 'T', 'r', 'm'], ['c', 'm', '8', 'T', 'r', 'm'], ['t', 'm', '8', 'T', 'r', 'm']]
|
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].
Input: Consider Input: question: What color is the largest object in the image ?
Output: #1 return largest object
#2 return color of #1
Input: Consider Input: question: How many days after the negotiating of the Anglo-Irish Treaty did the entire island of Ireland become the Irish Free State?
Output: #1 return the negotiating of the Anglo-Irish Treaty
#2 return the entire island of Ireland become the Irish Free State
#3 return day of #1
#4 return day of #2
#5 return the difference of #4 and #3
Input: Consider Input: question: If the left and right image contains the same number of cell phones.
| Output: #1 return the left image
#2 return the right image
#3 return cell phones in #1
#4 return cell phones in #2
#5 return number of #3
#6 return number of #4
#7 return if #5 is equal to #6
|
You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Galician.
Q: يمكنا التنبؤ بذلك تماماً.
A: Totalmente predicible.
****
Q: وهل ستعطيهم مكافأة لكونهم من ذوي العاطفة ؟
A: E ¿pagaríaselles un bonus por ser empáticos?
****
Q: اختيار هذا الخيار يعني أن الغالبية العظمى من المعرفة والحكمة المتراكمة ستكون متاحة لأي فرد أكثر بكثير مما ستتيحه عائلة بمفردها أو شخص بمفرده.
A: | Escollermos esta opcións significaría que unha inxente bolsa de coñecemento e sabedoría acumulada estaría ao dispor de calquera individuo en comparación co que xurdiría desde dentro dunha pequena familia ou un individuo en particular.
****
|
In this task, you will be given a list. The list is several integers and letters separated with a comma, written within a []. You can create new lists by dropping one of the items in the input list. Your task is to write a list containing all the possible lists you can make by dropping one item from the input list. For example, if the input list contains two items, you can drop one of the items each time. So the output should be a list comprising two inner lists that you have created by decreasing the items.
--------
Question: ['o', 'd', '5', 'e', 'H', '6', '5']
Answer: [['o', 'd', '5', 'e', 'H', '6'], ['o', 'd', '5', 'e', 'H', '5'], ['o', 'd', '5', 'e', '6', '5'], ['o', 'd', '5', 'H', '6', '5'], ['o', 'd', 'e', 'H', '6', '5'], ['o', '5', 'e', 'H', '6', '5'], ['d', '5', 'e', 'H', '6', '5']]
Question: ['4', '1', 'l', 'y', 'R']
Answer: [['4', '1', 'l', 'y'], ['4', '1', 'l', 'R'], ['4', '1', 'y', 'R'], ['4', 'l', 'y', 'R'], ['1', 'l', 'y', 'R']]
Question: ['m', '8', '4']
Answer: | [['m', '8'], ['m', '4'], ['8', '4']]
|
Detailed Instructions: Given two entities as input, classify as "yes" if second entity is the part of the first entity. Otherwise classify them as "no". These are entities of meronym In linguistics, meronymy is a semantic relation between a meronym denoting a part and a holonym denoting a whole. In simpler terms, a meronym (i.e., second entity) is in a part-of relationship with its holonym (i.e., first entity).
Problem:Entity 1: pollutant
Entity 2: particle
Solution: | yes |
Instructions: In this task, we have Spanish and Catalan tweets for automatic stance detection. The data has three labels Against, Favor, and Neutral which express the stance towards the target -independence of Catalonia. If the tweet criticizes the independence of Catalonia then it's 'Against' and if the tweets support it then it will be labeled as 'Favor' also if the tweets state information or news rather than stating opinion then it will be characterized as 'Neutral'.
Input: Tweet: @xavierps7 Perquè cert relat mediàtic ha fet pensar que els talls tenen mes a veure amb una actuació (política) dels mossos, i no amb les dinàmiques de mobilització.
Output: | Against |
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].
Input: Hey there! It's drama in Cody's Lab! Today we discuss whether or not incest is morally wrong. But can it also be morally neutral?
Output: | no |
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.
In this task, you are given two strings A,B. You must perform the following operations to generate the required output list: (i) Find the longest common substring in the strings A and B, (ii) Convert this substring to all lowercase and sort it alphabetically, (iii) Replace the substring at its respective positions in the two lists with the updated substring.
bYubMFxyTqR, AcDbMFxSnI
Solution: bYubfmxyTqR, AcDbfmxSnI
Why? Here, 'bMFx' is the longest common substring in both the input strings 'bYubMFxyTqR' and 'AcDbMFxSnI'. Sorting it and converting to lowercase gives 'bfmx'. Replacing 'bfmx' instead of 'bMFx' in the two strings gives 'bYubfmxyTqR' and 'AcDbfmxSnI'
New input: wGdtZSgdvkq, HutZSgeY
Solution: | wGdgstzdvkq, HugstzeY |
Detailed Instructions: 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.
See one example below:
Problem: A case is reported of a child with fatal pulmonary fibrosis following BCNU therapy.
Solution: adverse drug event
Explanation: Here, the child is facing some trouble after undergoing a particular therapy, thereby causing an adverse effect of the therapy.
Problem: Brain abscess following insertion of skull traction.
Solution: | non-adverse drug event |
You will be given a definition of a task first, then some input of the task.
For the given English description, write an SQL command such that it accomplishes every step. An SQL query works by selecting data from a table where certain conditions apply. A table contains columns where every row in that table must have a value for each column. Every table has a primary key that uniquely identifies each row, usually an id. To choose which columns are returned you specify that after the "SELECT" statement. Next, you use a "FROM" statement to specify what tables you want to select the data from. When you specify a table you can rename it with the "AS" statement. You can reference that table by whatever name follows the "AS" statement. If you want to select data from multiple tables you need to use the "JOIN" statement. This will join the tables together by pairing a row in one table with every row in the other table (Cartesian Product). To limit the number of rows returned you should use the "ON" statement. This will only return rows where the condition specified after the statement is true, this is usually an equals operator with primary keys. You can also use the "WHERE" statement to specify that only rows with column values statisfying a certain condition, should be returned. The "GROUP BY" statement will group rows together that have equal column values for whatever columns follows the statement. The "HAVING" statement will return groups that statisfy whatever condition follows the statement. Any column(s) being returned from grouped rows must either be an aggregate function, (AVG, MAX, COUNT, SUM, ...) of a column, or the column(s) that the data was grouped by. To sort the returned data you can use the "ORDER BY" command which will order the data by whatever aggregate function or column follows the statement. The "DESC" statement will sort in descending order and the "ASC" statement will sort in ascending order. Finally, you can use the "LIMIT" statement to return a certain number of rows. When "*" is used in an SQL statement every column is returned. For example, SELECT * FROM table WHERE attribute = 1, will select every column from rows with the attribute column equal to 1.
Did M0 's cinematographer , art director , and executive producer executive produce M1 , M2 , M3 , and M4
Output: | SELECT count(*) WHERE {
?x0 ns:film.cinematographer.film M0 .
?x0 ns:film.film_art_director.films_art_directed M0 .
?x0 ns:film.producer.films_executive_produced M0 .
?x0 ns:film.producer.films_executive_produced M1 .
?x0 ns:film.producer.films_executive_produced M2 .
?x0 ns:film.producer.films_executive_produced M3 .
?x0 ns:film.producer.films_executive_produced M4
} |
Detailed Instructions: 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.
See one example below:
Problem: A case is reported of a child with fatal pulmonary fibrosis following BCNU therapy.
Solution: adverse drug event
Explanation: Here, the child is facing some trouble after undergoing a particular therapy, thereby causing an adverse effect of the therapy.
Problem: Parkinsonian features were progressive, even after the patients had stopped work.
Solution: | non-adverse drug event |
Detailed Instructions: In this task you will be given a list of numbers and you need to find the mean (average) of that list. The mean of a list can be found by summing every number in the list then dividing the result by the size of that list. The output should be rounded to 3 decimal places.
Q: [100.115, -51.525, -19.534, 80.669, 209.359, -4.132, 35.93]
A: | 50.126 |
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.
Example: The fact that you do not want to donate to these poor, needy people only shows me that you really do not care about the embryos
Example solution: Invalid
Example explanation: It is not an argument on the topic of death penalty.
Problem: Only .06% of people who have killed kill again when they escape, are released, etc.
| Solution: Valid |
Given a premise, an initial context, an original ending, and a counterfactual context, the task is to generate a new story ending aligned with the counterfactual context and as close to the original ending as possible. Each instance consists of a five-sentence story. The premise is the first sentence of a story, and the second sentence, which is the initial context, provides more information about the story's context and the story's general plot. The original ending is the last three sentences of the story. Also, a counterfactual context is a slight modification to the initial context. You should write a new story ending that edits the original story ending as little as possible to regain coherence with the counterfactual context. To sum up, you should write the last three sentences of a story based on the premise(first sentence) and the counterfactual context(second sentence) of the story.
Q: Premise: Sara went to a concert with her friends.
Initial Context: They had good tickets but there were many tall people in front.
Original Ending: They stood on chairs to see the stage. The ushers told them to get down. Sara was disappointed that they could not see the stage well.
Counterfactual Context: They had front row tickets.
A: They stood on chairs to see the stage even better The ushers told them to get down. Sara understood that others could not see the stage .
****
Q: Premise: When a new girl starts attending Alex's school he thinks she's pretty.
Initial Context: Alex pretends to be a feminist to get her to go out with him.
Original Ending: It works at first. But when she finds out that he's not a feminist she dumps him. Alex is kind of glad because he hated pretending to be a feminist
Counterfactual Context: Alex never did get to go out with her.
A: Alex was too shy to ask her out. But when he found out her attitude he lost his interest. Alex is a conservative type of guy.
****
Q: Premise: Sean and Sara decided to bake crackers.
Initial Context: They looked up a recipe.
Original Ending: Then, they put it all together. They put it in the oven and baked the dough. Then, they ate the crackers with cheese.
Counterfactual Context: Then they decided they would rather have a cake so they made that instead.
A: | Then, they put all of the ingredients together. They put it in the oven. Then, they ate the cake with milk.
****
|
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: Consider Input: " Dat heeft niets te maken met SBS , maar wel met de waardering van UPC op de beurs .
Output: None
Input: Consider Input: Wanneer door de darmvulling de druk in het uiteinde van de dikke darm oploopt en stijgt tot ergens tussen de 2,5 en de 6,5 kilopascal , een druk vergelijkbaar met 2,5 tot 6,5 procent van de luchtdruk , start de defecatiereflex .
Output: None
Input: Consider Input: Het waren de Modern Times van de lopende band , de chronometer en de drie-keer-achturendag .
| Output: None
|
Detailed Instructions: Given a part of privacy policy text, identify the purpose for which the user information is collected/used. The purpose should be given inside the policy text, answer as 'Not Specified' otherwise
Problem:The site collects your location information for personalization or customization. Collection happens when you implicitly provide information on the website.
Solution: | Personalization/Customization |
Given the sentence, generate "yes, and" response. "Yes, and" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated ("Yes") and then expand on that line of thought or context ("and..."). 1 In short, a "Yes, and" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a "Yes, and" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'.
[Q]: Beth, that woman looks like Alyssa's friend who left not long after the stoning. But she's got a different attitude.
[A]: God damn it. Excuse me, are you that fucking tree possessing another fucking person?
[Q]: Congratulations on the hand maids teaching you what slavery was.
[A]: It's like, now I get it. Those were good lessons.
[Q]: I miss music. I just miss hearing music. Don't you?
[A]: | I do agree with you. That was one thing I had a lot of in the woods. Concerts.
|
Definition: In this task, we ask you to parse restaurant descriptions into a structured data table of key-value pairs. Here are the attributes (keys) and their examples values. You should preserve this order when creating the answer:
name: The Eagle,...
eatType: restaurant, coffee shop,...
food: French, Italian,...
priceRange: cheap, expensive,...
customerRating: 1 of 5 (low), 4 of 5 (high)
area: riverside, city center, ...
familyFriendly: Yes / No
near: Panda Express,...
The output table may contain all or only some of the attributes but must not contain unlisted attributes. For the output to be considered correct, it also must parse all of the attributes existant in the input sentence; in other words, incomplete parsing would be considered incorrect.
Input: Near The Bakers is a Japanese restaurant called The Golden Curry that is kids friendly and has food for 20-25 dollars.
Output: | name[The Golden Curry], food[Japanese], priceRange[£20-25], familyFriendly[yes], near[The Bakers] |
In this task, we have Spanish and Catalan tweets for automatic stance detection. The data has three labels Against, Favor, and Neutral which express the stance towards the target -independence of Catalonia. If the tweet criticizes the independence of Catalonia then it's 'Against' and if the tweets support it then it will be labeled as 'Favor' also if the tweets state information or news rather than stating opinion then it will be characterized as 'Neutral'.
Q: Tweet: 🔴 DIRECTE | Es reprèn l'interrogatori a l'exconseller d'Interior Joaquim Forn #JudiciProcés ⚖️ https://t.co/zOYrGBukZL
A: Favor
****
Q: Tweet: RT @QuicoSalles: La mala traducció d’un informe dels @Mossos, prova de descàrrec de Forn. Pompeu Fabra deixa en evidència l'Estat https://t…
A: Neutral
****
Q: Tweet: Cal parar ja aquesta deriva de divisió i enfrontament que posa en perill la convivència de la societat catalana. Tots els demòcrates hem de participar activament en evitar aquesta fractura #quenoensenfrontin Recomenable article de Sergi Pamies https://t.co/dp79SrhGTC
A: | Against
****
|
Detailed Instructions: In this task, we have Spanish and Catalan tweets for automatic stance detection. The data has three labels Against, Favor, and Neutral which express the stance towards the target -independence of Catalonia. If the tweet criticizes the independence of Catalonia then it's 'Against' and if the tweets support it then it will be labeled as 'Favor' also if the tweets state information or news rather than stating opinion then it will be characterized as 'Neutral'.
See one example below:
Problem: Tweet: Vull votar i votaré. Hi ha quelcom que no em permet no fer-ho. Ara bé tinc un greu problema. No sé a qui!!
Solution: Favor
Explanation: The tweet asks for the right to vote for the independence of Catalonia and it supports the movement so it will be characterized as 'Favor'.
Problem: Tweet: #VagaFeminista8M | Davant l’avenç de propostes i mesures de govern misògines, LGBTIfòbiques i racistes, la vaga feminista d'aquest #8M serà llegida com una mostra del pols que pot jugar la manada violeta contra la regressió de drets. Per @TxellRigol https://t.co/1Oh4qu8AEq
Solution: | Favor |
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
2508 @ 2806 @ 4837 | 10151 |
Given the task definition and input, reply with output. Given an adjective, generate its antonym. An antonym of a word is a word opposite in meaning to it.
following
| leading |
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
Input: Consider Input: we have assumed that the anticompetitive conduct here independently caused foreign injury; that is, the conduct's domestic effects did not help to bring about that foreign injury.
Output: overruling
Input: Consider Input: no other third floor workers, who also worked without breathing apparatus, complained of respiratory symptoms.
Output: non-overruling
Input: Consider Input: because the warrant was supported by probable cause, we reverse the order granting the motion to suppress and remand the case for proceedings not inconsistent with this opinion.
| Output: non-overruling
|
Instructions: You are given a password and you need to generate the number of steps required to convert the given password to a strong password. A password is considered strong if (a) it has at least 6 characters and at most 20 characters; (b) it contains at least one lowercase letter and one uppercase letter, and at least one digit; (c) it does not contain three repeating characters in a row. In one step you can: (1) Insert one character to password, (2) delete one character from password, or (3) replace one character of password with another character.
Input: password = WEGVQJFede.mO
Output: | 1 |
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'.
Q: Een deelnemer laat zich verleiden tot het snel rijden buiten de piste , zijn achterwiel en voorwiel komen terecht in een verschillend spoor en de val die daarop volgt , is zeer hard .
A: | None |
Detailed Instructions: 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.
See one example below:
Problem: customer: Hello.
agent: Hello. How may I help you?
customer: I would like to do some changes in my existing reservation, can you please help me out?
agent: Sure, I will help you in booking. May I know your name to proceed further?
__
agent: Alexander Hernandez, regret to inform that there is no active reservation found under your name to amend.
customer: That's ok, no problem. Thank you for the information.
agent: Thank you for reaching us.
Solution: customer: Sure, myself Alexander Hernandez.
Explanation: This is pretty forward, based on the answer after the blank, the answer would be to know the name of the person, and the name is mentioned in the next dialogue to the blank
Problem: customer: Hello.
agent: Hello.
customer: Stephanie Lewis here.
agent: How can I help you?
customer: I want to travel from EWR to JFK for my business conference, can you please reserve a flight ticket on those locations?
agent: Sure, may I know your travelling dates please?
customer: Ok, my departure is on Apr 16 and please book my return ticket also on Apr 18.
__
customer: Yes, I will prefer single connection.
agent: How much can you afford for this ticket?
customer: I can afford up to 5000.
agent: Do you have any class preference?
customer: No.
agent: Please wait.
customer: Sure, take your time.
agent: Thank you for waiting, we found a flight with number 1004 and airline AA at a price of 200 with 1 connection. Shall I proceed?
customer: I am ok with this flight, you can proceed with booking now.
agent: Sure, your booking is done.
customer: Thank you for your assistance.
agent: Thank you for reaching us, have a good day.
Solution: | agent: Do you need a connection in between your journey? |
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'.
Q: Meer en meer gaat die de onvrede kanaliseren over alles wat er fout gaat in de Franse samenleving .
A: | None |
In this task, you will be given a list. The list is several integers and letters separated with a comma, written within a []. You can create new lists by dropping one of the items in the input list. Your task is to write a list containing all the possible lists you can make by dropping one item from the input list. For example, if the input list contains two items, you can drop one of the items each time. So the output should be a list comprising two inner lists that you have created by decreasing the items.
['O', 'l', 'd', '2', 'T'] | [['O', 'l', 'd', '2'], ['O', 'l', 'd', 'T'], ['O', 'l', '2', 'T'], ['O', 'd', '2', 'T'], ['l', 'd', '2', 'T']] |
Q: Your task is to localize given English phrase into Telugu language. When localising, follow these rules - (1) General names and concepts can be translated (2) Domain specific names can just be transliterated (3) Localised phrases can have both partial translated and transliterated parts (4) But only partial translation or only partial transliteration is not allowed (5) Copy special characters and numbers as is
Size & & Orientation
A: | కొలత & & దిక్సాధన |
Given the question: Generate a 3-star review (1 being lowest and 5 being highest) about an app with package com.fsck.k9.
The answer is: | Scroll button inhibits favs The scroll button on the right is activated when attempting to """"""""star"""""""" an email. HTC A9 on Marshmallow."" |
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.
Q: Content:Режисьорът Бари Дженкис, чийто филм тази година беше един от големите победители на „Оскари”-те, издаде, че в момента работи върху екранизацията на бестселър за бягството от робството.
A: | Режисьорът на „Лунна светлина” ще заснеме нова ... |
Detailed Instructions: In this task you are given a list of numbers and you need to find the average of each two consecutive values. The average of two numbers a and b is calculated as: (a + b) /2. The output should be a list of the averages of each two consecutive values. A list is presented with two brackets and comma-separated values, like: [1,2,3].
Q: [38, -89, -99, -76, 100, -4, 96]
A: | [-25.5, -94.0, -87.5, 12.0, 48.0, 46.0] |
Q: 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.
Concept: dove, Relatum: robin.
A: | coord |
Instructions: 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.
Input: Content:Днес, ще ви кажа как да си приготвите най-известния десерт в света – тирамису. Ще ви разкрия няколко тайни, за да ви помогна да спестите много средства и време, например как да си приготвите нежен аналог на сиренето маскарпоне. Само си представете как се топи в устата … Как да си приготвим тирамису в домашни условия? Продукти: 250 грама маскарпоне 50 грама захар 250 мл сметана 2 яйца 6 броя бишкоти 200 грама консервирани или замразени череши (малини, ягоди) 200 мл прясно сварено кафе 500 грама млечен шоколад Приготвяне: Ако цената на сиренето маскарпоне ви смущава, то си пригответе неговия аналог. Вземете 150-200 грама извара, 50 мл сметана, 2 яйца, 50 грама пудра захар. Първо, разбийте изварата, след това – жълтъците и половината пудра захар, после белтъците и втората половина пудра захар, и накрая сметаната. Всички съставки трябва да се смесят в кремообразна еднородна маса. Разделете жълтъците от белтъците и ги смесете с маскарпонето и захарта. Всичко се разбърква добре. Разбийте с миксера белтъците със сметаната. Смесете двете смеси и кремът е готов. Сега вземете две пластмасови бутилки, измийте ги добре и отрежете горната част, така че да се получи нещо като чаша. Отрежете част от стените на всяка от “чашите”. Сега свържете двете части на бъдещата форма, така, както е показано на картинката. Напълнете формата с приготвения крем наполовина. Само не яжте, докато десертът не стане готов. Сега сложете плодовете в средата. Потопете бишкотите в кафето и ги сложете върху плодовете. Сега сложете втората половина от крема. Добавете още плодове по краищата. Отгоре сложете пак бишкоти, потопени в кафе. Сега сложете бъдещия си десерт за 3 часа в хладилника, така че да стегне добре. Тогава го извадете от формата. Става много лесно – само разделяте една от друга бутилките. Ето един трик! Разтопете шоколада на водна баня и полейте десерта. Украсете тирамисуто с плодове. Непременно направете този прекрасен десерт! Той е толкова нежен и вкусен, че е трудно да се задоволите само с едно парче. Получава се лек и приятен.
Output: | Не мога да си представя живота без най- вкусния десерт, който може да оправи и най- скучния и най- лошия ми ден |
Definition: 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.
Input: [-97.868 -52.189 -19.065 -10.925 17.903 -13.681]
Output: | -97.868 |
In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the alphabetical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no alphabetical element is in the list.
Q: ['D', 'u', '7817']
A: | 1, 2 |
Generate a 3-star review (1 being lowest and 5 being highest) about an app with package net.sourceforge.opencamera.
A: | Selfie le le |
Teacher: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].
Teacher: Now, understand the problem? Solve this instance: question: Are there more tiny blue spheres then cubes?
Student: | #1 return tiny spheres
#2 return #1 that are blue
#3 return cubes
#4 return number of #2
#5 return number of #3
#6 return if #4 is higher than #5 |
In this task, you are given commands (in terms of logical operations) and natural interpretation of the given command to select relevant rows from the given table. Your job is to generate a label "yes" if the interpretation is appropriate for the command, otherwise generate label "no".
Here are the definitions of logical operators:
1. count: returns the number of rows in the view.
2. only: returns whether there is exactly one row in the view.
3. hop: returns the value under the header column of the row.
4. and: returns the boolean operation result of two arguments.
5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column.
6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column.
7. argmax/argmin: returns the row with the max/min value in header column.
8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column.
9. eq/not_eq: returns if the two arguments are equal.
10. round_eq: returns if the two arguments are roughly equal under certain tolerance.
11. greater/less: returns if 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.
One example: Command: eq { hop { nth_argmax { all_rows ; attendance ; 3 } ; competition } ; danish superliga 2005 - 06 }, interpretation: select the row whose attendance record of all rows is 3rd maximum. the competition record of this row is danish superliga 2005-06.
Solution is here: yes
Explanation: Here, the command and interpretion given for the command is correct that 3rd maximum should be selected from given table rows. Hence, the label is 'yes'.
Now, solve this: Command: eq { count { filter_greater { all_rows ; year ; 2000 } } ; 3 }, interpretation: select the row whose agg record of all rows is maximum . the team 1 record of this row is canon yaoundé .
Solution: | no |
Subsets and Splits