prompt
stringlengths 45
13.4k
| response
stringlengths 0
2.99k
|
|---|---|
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].
[28, 0, 32] | [14.0, 16.0] |
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].
Example Input: Monarchism the only true answer to these trying times. Can we all stop shendaposting for one minute to come together and elect a king?
Example Output: no
Example Input: > Smuggies are single paneled MS Paint drawings of a character presenting one or more outlandish and/or conflicting ideas in a smug way. Basically really bad memes, apparently all by bigots/incels if you go by their top/all time posts.
Example Output: yes
Example Input: LongPostBot is back? Effortcels on suicide watch.
Example Output: | no
|
In this task you will be given an arithmetic operation and you have to find its answer. The operators '+' and '-' have been replaced with new symbols. Specifically, '+' has been replaced with the symbol '@' and '-' with the symbol '#'. You need to perform the operations in the given equation return the answer
[Q]: 519 @ 9686 @ 3145 # 9320
[A]: 4030
[Q]: 7936 @ 9333 @ 6122 @ 6291 # 210
[A]: 29472
[Q]: 4068 # 6331 @ 7928
[A]: | 5665
|
Given the question: Generate a 3-star review (1 being lowest and 5 being highest) about an app with package de.danoeh.antennapod.
The answer is: | This app was amazing but it no longer saves my place in the middle of a podcast so its not really usable for me anymore. |
Part 1. Definition
Two analogies that relate objects to the associated rooms is given in the form "A : B. C : ?". "A : B" relates object A to room B. Your task is to replace the question mark (?) with the appropriate room for the given object C, following the "A : B" relation.
Part 2. Example
shelf : nursury. cabinet : ?
Answer: bathroom
Explanation: The given analogy relates objects to their rooms. A shelf is associated with a nursery. A cabinet is associated with a bathroom
Part 3. Exercise
workbench : garage. sofa : ?
Answer: | parlor |
Q: 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
state v. jefferson, supra; state v. williams, supra and state v. beard, supra, are therefore overruled to the extent that they are in conflict with this opinion.
A: | overruling |
Which movie is the following review about?
An extraordinary embodiment of the period, [Johansson] looks to have stepped right into a Vermeer frame.
Movie: | girl with a pearl earring |
TASK DEFINITION: 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...'.
PROBLEM: You're charging us with magic, and magic doesn't exist. So we don't believe you.
SOLUTION: Do you believe you're going to jail? Because you're going to jail.
PROBLEM: Jimmy, are you calling yourself Dillon on the phone again?
SOLUTION: Dillon's my cool name. Dillon Tristan.
PROBLEM: Which episode of Good Times were you going to show?
SOLUTION: | You know, the black Jesus episode. But, please enlighten us with your European history.
|
Given the task definition and input, reply with output. 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.
Command: round_eq { avg { all_rows ; attendance } ; 58746 }, interpretation: the average of the attendance record of all rows is 58746 .
| yes |
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.
Let me give you an example: [0,1,0,2,5,1]
The answer to this example can be: [2,5]
Here is why: The only elements that are not duplicated is 2 and 5. This is a good example.
OK. solve this:
[1, 6, 7, 0, 0, 1, 4, 4, 3]
Answer: | [6, 7, 3] |
Instructions: 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.
Input: ['5907', 'Y', 'C', 't']
Output: | 2, 3, 4 |
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.
Example: Find the id and city of the student address with the highest average monthly rental.
Example solution: SELECT T2.address_id , T1.city FROM Addresses AS T1 JOIN Student_Addresses AS T2 ON T1.address_id = T2.address_id GROUP BY T2.address_id ORDER BY AVG(monthly_rental) DESC LIMIT 1
Example explanation: First we select the student's id and city of their address. Next, to find where each student lived we must join the "Addresses" table with the "Student_Addresses" table on rows with the same "address_id". Finally, we want to return the student address with the highest monthly rent. This is a good example.
Problem: How many different kinds of clients are supported by the web clients accelerators?
| Solution: SELECT count(DISTINCT client) FROM web_client_accelerator |
Read the given sentence and if it is a general advice then indicate via "yes". Otherwise indicate via "no". advice is basically offering suggestions about the best course of action to someone. advice can come in a variety of forms, for example Direct advice and Indirect advice. (1) Direct advice: Using words (e.g., suggest, advice, recommend), verbs (e.g., can, could, should, may), or using questions (e.g., why don't you's, how about, have you thought about). (2) Indirect advice: contains hints from personal experiences with the intention for someone to do the same thing or statements that imply an action should (or should not) be taken.
I think the better question is " do you love yourself ? " | no |
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.
This report presents a patient with membranoproliferative glomerulonephritis (MPGN) who developed KS following treatment with long-term medium dose glucocorticoid and short-term additional immunosuppressives. | non-adverse drug event |
Detailed Instructions: Given a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. For commands, 'left' and 'right' are used to denote the direction of an action. opposite turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. Actions and commands do not have quotations in the input and output.
Q: I_TURN_LEFT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK
A: | look left and look around right twice |
You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Galician.
(ضحك) هذه صورة جميلة ، لأن هؤلاء طلاب يأتون إلى المدرسة بعد الحصص
(Risas) DP: Esta é boa porque son estudantes indo á escola despois de clase.
وعائلاتهم ، الضحايا الخفية للمرض ، مشغولة برعايتهم ليلا و نهارا ومنهكة للخروج والمطالبة بالتغيير ،
E as súas familias, as vítimas ocultas, a coidar aos seres queridos día e noite, están a miúdo demasiado cansas para saír defender o cambio.
سبب وجود هذه الصورة هنا ، هذه الأشعة السينية ، فقط لأخبركم عن أين وكيف كنا نطالع الأشعة السينية.
| A razón de que estea esta imaxe aquí, esta radiografía, é para que vexan as condicións nas que estábamos.
|
Teacher: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".
Teacher: Now, understand the problem? Solve this instance: Japanese: 「彼らの顔を知っている人、宝石のありかを知っている人、またはその他の情報を持っている人は、我々に連絡してほしい。」
Thai: จูเลีย กิลลาร์ดได้ขึ้นมาแทนที่รัดด์ทั้งในตำแหน่งหัวหน้าพรรคแรงงานออสเตรเลีย และตำแหน่งนายกรัฐมนตรีออสเตรเลียเมื่อเดือนกรกฎาคม 2010
Student: | No |
In this task you will be given a list of integers. A list contains numbers separated by a comma. You need to round every integer to the closest power of 2. A power of 2 is a number in the form '2^n', it is a number that is the result of multiplying by 2 n times. The following are all powers of 2, '2, 4, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096'. If an integer is exactly in equally far from two different powers of 2 then you should output the larger power of 2. The output should be a list of integers that is the result of rounding each integer int the input list to the closest power of 2. The output should include a '[' to denote the start of the output list and ']' to denote the end of the output list.
Example input: [16, 205, 171, 2, 9, 317]
Example output: [16, 256, 128, 2, 8, 256]
Example explanation: Every integer in the input list is rounded to the nearest power of 2. The number 2 and 16 are in the input list and both are a power of 2, therefore rounding to the closest power of 2 returns the same number. This is a good example.
Q: [116, 1218, 3381, 3966, 15, 30, 4, 233, 1734, 4766, 2292, 13]
A: | [128, 1024, 4096, 4096, 16, 32, 4, 256, 2048, 4096, 2048, 16] |
Detailed Instructions: 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.
See one example below:
Problem: কোনো মেয়ে ইসলাম ধর্ম গ্রহণ করলে আমি তাকে বিয়ে করতে রাজি(আমি কুরআন হাফেজ)।
Solution: religious
Explanation: Here it expresses hate against the religion, hence tagged as religious.
Problem: ডুবন্ত নৌকায় আর এক বলদ সাকিব
Solution: | non-religious |
Given the task definition, example input & output, solve the new input case.
You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Galician.
Example: ويوجد أساسا مرجل دوار.
Output: É basicamente un caldeiro que rota.
The Arabic sentence is correctly translated into Galician, because the meaning is preserved.
New input case for you: ويتم صب المرايا الذائبة وتبريدها شيئا فشيئا ، وتم صقلها بدقة رائعة.
Output: | Os espellos fúndense e arrefrían moi lentamente, e despois pólense con extrema precisión. |
Detailed Instructions: 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
See one example below:
Problem: 6 @ 17
Solution: 23
Explanation: Here, '@' represents the addition operation. So, the answer is 23 (6+17=23).
Problem: 5774 @ 5324 # 3038 @ 7107 @ 9031
Solution: | 24198 |
Detailed Instructions: The provided text is in English, and we ask you to translate the text to the Croatian language. Please bear in mind the following guidelines while translating: 1) We want a natural translation, a formal form. 2) Use the symbols like '#@%$-+_=^&!*' as-is. *Include* the special characters as suited when translating to Croatian. 3) Quantities like millions or billions should be translated to their equivalent in Croatian language 4) Note the input is all case-sensitive except for special placeholders and output is expected to be case-sensitive. 5) The output must have Croatian characters like Ž or č and the output must preserve the Croatian language characters. 6) The input contains punctuations and output is expected to have relevant punctuations for grammatical accuracy.
Q: We all love chocolate.
A: | Svi mi volimo čokoladu. |
Please answer this: Generate a 4-star review (1 being lowest and 5 being highest) about an app with package org.telegram.messenger.
++++++++
Answer: Best chat
Problem: Generate a 5-star review (1 being lowest and 5 being highest) about an app with package com.google.android.diskusage.
A: Best app This is probably the best app on the market for working out how much of your storage space is taken by what. The graphical interface is simple to understand and just works.
Problem: Given the question: Generate a 5-star review (1 being lowest and 5 being highest) about an app with package org.ppsspp.ppsspp.
++++++++++++++++++++++++++++++++
The answer is:
How to load just download rar after downloading your PSP game enter to rar and go to the game and extract it find it out on YouTube
input question: Generate a 3-star review (1 being lowest and 5 being highest) about an app with package de.j4velin.wifiAutoOff.???
output answer: Is it nice I don't now
Generate a 5-star review (1 being lowest and 5 being highest) about an app with package org.telegram.messenger.
----
Answer: great
Q: Generate a 1-star review (1 being lowest and 5 being highest) about an app with package com.google.android.gms.
A: | Super Všechno bezi tak jak má |
Instructions: 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
Input: 2677 @ 2985 # 4137 @ 3098 @ 56
Output: | 4679 |
Teacher: 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...'.
Teacher: Now, understand the problem? If you are still confused, see the following example:
I just want to say if this does not work out I promise to to personally show up to each of your homes and apologize for my life not working out the way that it should.
Solution: You know what, come tell us at the community pool.
Reason: This is a good response. Because it accepts in indirect way the input sentence and supports it.
Now, solve this instance: Denise, I heard from the other teachers that your performance in their classes is suffering, as well. I also heard there was an incident in the gymnasium.
Student: | Well, yeah. We were all in the gymnasium and everybody said, "Hey, Denise, turn around!" So, I did, and then they all just hit me with their balls. |
In this task, you need to answer 'Yes' if the given word is the longest word (in terms of number of letters) in the given sentence, else answer 'No'. Note that there could be multiple longest words in a sentence as they can have the same length that is the largest across all words in that sentence.
Ex Input:
Sentence: 'three zebras mill about in a grassy enclosure'. Is 'enclosure' the longest word in the sentence?
Ex Output:
Yes
Ex Input:
Sentence: 'these trains are riding on a railroad track next to each other'. Is 'railroad' the longest word in the sentence?
Ex Output:
Yes
Ex Input:
Sentence: 'a sign on a city store that reads pruyn pronounced prine'. Is 'pronounced' the longest word in the sentence?
Ex Output:
| Yes
|
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'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.
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.
Why? 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
New input: customer: Hello.
agent: Hello, how may I aid you?
customer: I am planning to book a flight ticket to DEN from PHX, can you please help me out?
agent: Sure, let me know your trip dates please?
__
agent: May I know your connection limit?
customer: Yes, I am looking for a flight with 1 connection.
agent: Do you have any time concern?
customer: No.
agent: Do you need any airline preference?
customer: No.
agent: Ok, is there any class preference?
customer: No issues with class.
agent: Can I know your name please?
customer: Sure, my name is Carol Adams.
agent: Frontier Airlines is providing connecting flight with the ticket fare of 200 and depart time is 14:00 hours, arrival time is 1:00 hours, Shall I proceed?
customer: Ok, please confirm my reservation.
agent: Your ticket has been confirmed by flight number 1018 and an economy class.
customer: Thank you for the help.
agent: Thanks for choosing us.
Solution: | customer: Sure, my planned travelling dates are Feb 22 and Feb 24. |
Given the task definition, example input & output, solve the new input case.
In this task, you will be presented with a premise sentence and a hypothesis sentence in Persian. Determine whether the hypothesis sentence entails, contradicts, or is neutral with respect to the given premise sentence. Classify your answers into "Contradiction", "Neutral", or "Entailment".
Example: Premise: و شما می دانید مردم می گویند که می دانید فرستادن بچه ها به کالج گران است ، اما اگر همه مسئولیت کمی را بر عهده داشته باشند می دانید که هزینه آن در حدود پانصد دلار در هر ترم است ، فرض کنید که به یک کالج ایالتی بروند و در خانه زندگی کنند <sep> Hypothesis: مردم می گویند کالج گران است.
Output: Entailment
This is a good example, and the hypothesis sentence entails the given premise sentence.
New input case for you: Premise: برای اولین بار ، ایستگاه های تلویزیونی به مرحله ای رسیدند که ۲۴ ساعت شبانه روز تبلیغات نشان می دادند. <sep> Hypothesis: ایستگاه های تلویزیونی دیگر هیچ تبلیغی نشان ندادند.
Output: | Contradiction |
In this task, you will be shown an English sentence. You need to classify the sentence as either a representation of an anaphor number agreement or as an incorrect representation. An anaphor is an expression whose interpretation depends upon another expression. Anaphor number agreement is a restriction where a phrase agrees with the preceeding expression: plurals match plurals or singular expressions match singular expressions. In this task a valid representation of anaphor number agreement should be denoted as 'good' while everything else should be denoted as 'bad'. A correct representation of an anaphor number agreement will be a grammatically correct instance of a sentence where the subject and self-referencing nouns match plurality. An incorrect representation is a sentence in which the subject and self-referencing noun's plurality do not match.
Let me give you an example: Bob helped himself to some food.
The answer to this example can be: good
Here is why: The use of himself agrees with the singular subject Bob.
OK. solve this:
Steve insulted themselves.
Answer: | bad |
Given an adjective, generate its antonym. An antonym of a word is a word opposite in meaning to it.
Let me give you an example: able
The answer to this example can be: unable
Here is why: The output is correct as able and unable are opposities of each other in meaning.
OK. solve this:
inductive
Answer: | deductive |
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
Ex Input:
to the extent treadwell, supra at 742743, 684 s.e.2d 244 and wilkes v. state, 293 ga.app. 724, 726(2), 667 s.e.2d 705 (2008) can be interpreted to hold otherwise, they are overruled.
Ex Output:
overruling
Ex Input:
however, because the stalking statute proscribes an entire course of conduct, ""a second or successive offense is not necessarily committed by acts that are factually distinct from each other but only by acts that are factually distinct from the entire course of conduct punished by the first conviction.""
Ex Output:
non-overruling
Ex Input:
lopez asks that we reconsider dennis in light of studies that ""conclude children are highly susceptible to suggestive questioning techniques like repetition, guided imagery, and selective reinforcement.""
Ex Output:
| non-overruling
|
Given the task definition and input, reply with output. 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.
Command: eq { hop { nth_argmax { all_rows ; games ; 2 } ; player } ; david gonzalvez }, interpretation: select the row whose games record of all rows is 2nd maximum . the player record of this row is david gonzalvez .
| yes |
You will be given a definition of a task first, then some input of the task.
In this task, you need to answer 'Yes' if the given word is the longest word (in terms of number of letters) in the given sentence, else answer 'No'. Note that there could be multiple longest words in a sentence as they can have the same length that is the largest across all words in that sentence.
Sentence: 'frontal view of airplane with cockpit facing on white airplane'. Is 'of' the longest word in the sentence?
Output: | No |
Given the task definition and input, reply with output. Given a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. For commands, 'left' and 'right' are used to denote the direction of an action. opposite turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. Actions and commands do not have quotations in the input and output.
I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK
| turn opposite left thrice and walk around left twice |
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.
[5, 4, 6, 1, 6, 6, 0, 0, 1, 7] | [5, 4, 7] |
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.
Input: Consider Input: [63, 6]
Output: []
Input: Consider Input: [16, -99, -20, 81, -94, -98, -70]
Output: [16, -20, -94, -98, -70]
Input: Consider Input: [-86, 33, 7, -65, 12]
| Output: [-86, 7, -65]
|
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].
--------
Question: [59, -64, -32, 17, -11, 56, 91, -44, 86, -59, -3, -8, 62, -66, 1]
Answer: [-2.5, -48.0, -7.5, 3.0, 22.5, 73.5, 23.5, 21.0, 13.5, -31.0, -5.5, 27.0, -2.0, -32.5]
Question: [74, 1, 0, -48, -70, -9, -5, -3, -96, 36, 63, -46, 87, 16, -82]
Answer: [37.5, 0.5, -24.0, -59.0, -39.5, -7.0, -4.0, -49.5, -30.0, 49.5, 8.5, 20.5, 51.5, -33.0]
Question: [-5, -93, 84, -24, -72]
Answer: | [-49.0, -4.5, 30.0, -48.0]
|
Detailed Instructions: In this task, you will be presented with a question in Dutch language, and you have to write the person names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Phrase used for the person name - PER. There can be instances with no person name entity, then return 'None'.
Problem:Waarom koos u voor Concentra ?
Solution: | None |
Given the task definition, example input & output, solve the new input case.
Two analogies that relate objects to the associated rooms is given in the form "A : B. C : ?". "A : B" relates object A to room B. Your task is to replace the question mark (?) with the appropriate room for the given object C, following the "A : B" relation.
Example: shelf : nursury. cabinet : ?
Output: bathroom
The given analogy relates objects to their rooms. A shelf is associated with a nursery. A cabinet is associated with a bathroom
New input case for you: counter : kitchen. nightstand : ?
Output: | bedroom |
Detailed Instructions: You are given a password and you need to generate the number of steps required to convert the given password to a strong password. A password is considered strong if (a) it has at least 6 characters and at most 20 characters; (b) it contains at least one lowercase letter and one uppercase letter, and at least one digit; (c) it does not contain three repeating characters in a row. In one step you can: (1) Insert one character to password, (2) delete one character from password, or (3) replace one character of password with another character.
See one example below:
Problem: password = a
Solution: 5
Explanation: Using 5 steps, it can become a strong password
Problem: password = aJPgmGm6InXsRiFexc!VuUZckrVu8g0oezB8aU.
Solution: | 19 |
You will be given two sentences. One of them is created by paraphrasing the original one, with changes on an aspect, or using synonyms. Your task is to decide what is the difference between two sentences. Types of change are explained below:
Tense: The verbs in the sentence are changed in tense.
Number: Plural nouns, verbs and pronouns are changed into single ones or the other way around.
Voice: If the verbs are in active voice, they're changed to passive or the other way around.
Adverb: The paraphrase has one adverb or more than the original sentence.
Gender: The paraphrase differs from the original sentence in the gender of the names and pronouns.
Synonym: Some words or phrases of the original sentence are replaced with synonym words or phrases. Changes in the names of people are also considered a synonym change. Classify your answers into Tense, Number, Voice, Adverb, Gender, and Synonym.
One example: original sentence: Lily spoke to Donna , breaking her silence . paraphrase: Lily is speaking to Donna , breaking her silence .
Solution is here: Tense
Explanation: The verbs in this example are changed from past tense to present tense.
Now, solve this: original sentence: Beth didn't get angry with Sally , who had cut her off , because she stopped and apologized . paraphrase: Beth and Emma didn't get angry with Sally and Lucy , who had cut them off , because they stopped and apologized .
Solution: | Number |
instruction:
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.
question:
News Headline: Meet the {billionaires} who run Trump 's government
Edit: Pigeons
answer:
Funny
question:
News Headline: Mike Pence Told About Flynn Warning Two Weeks After Trump , White {House}
Edit: Horse
answer:
Not Funny
question:
News Headline: Bill O'Reilly Taking a {Break} Amid Sponsor Backlash
Edit: smoke
answer:
| Not Funny
|
Given the task definition, example input & output, solve the new input case.
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).
Example: Entity 1: plant
Entity 2: leaf
Output: yes
The answer is correct. Because the leaf is part of the plant. Therefore, here leaf is meronym and the plant is holonym.
New input case for you: Entity 1: carbonaceous chondrite
Entity 2: zone
Output: | no |
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].
Example Input: What kind of retarded thought train wreck is that defense? No, you clearly didn't mean anything of the sort. "We should shoot all black people until we find a solution". No that's clearly not racist, because I meant shoot them a text with words of encouragement. But I didn't say that in the quote, did I? So the quote is still racist.
Example Output: yes
Example Input: I want to argue about transgender people more I feel like we're on the verge of finally settling the issue
Example Output: no
Example Input: I don't hate the rich, lol, just bailouts. And I actually have a very sexy dimple.
Example Output: | no
|
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.
Q: Andrew Laird: You know , Fallon ? Most little girls realize by the age of _ six _ that they ca n't grow up and marry their daddies . Friends should n't fight .
Fallon: You 're right . Bye , Andy .
A: AGE
****
Q: Detective Manners: That 's a bleepin ' dead alien body if I ever bleepin ' saw _ one _ .
A: REFERENCE body
****
Q: Lilly: Hauling _ two _ of your dead carcasses outta here is just as easy as hauling out one !
Lt. Harris Redding: Look now , hold on . Wait just a minute !
Lilly: Three do n't bother me none either !
A: | REFERENCE carcasses
****
|
Generate a 5-star review (1 being lowest and 5 being highest) about an app with package com.ruesga.android.wallpapers.photophase.
The answer to this question is: | Very good! Probably the best live Wallpaper I've ever had ! |
Indicate if the following Polish tweet contains cyber-bullying content with 'Yes'; otherwise, respond with 'No'.
Input: Consider Input: Tweet: Trójpodzial jest biblia państw demokratycznych , Question: Does the tweet contain cyberbullying (harmful) content?
Output: No
Input: Consider Input: Tweet: Dziś mam wolne, więc wszystko robię wolno i wszystko mi wolno! #TakaTeza , Question: Does the tweet contain cyberbullying (harmful) content?
Output: No
Input: Consider Input: Tweet: więc zaczynam oglądać Do wszystkich chłopców, których kochałam bo wszyscy o tym mówią i aż chcę to sprawdzić , Question: Is the tweet free of any cyberbullying (harmful) content?
| Output: Yes
|
Detailed Instructions: 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.
Problem:[189.382, 48.172, 183.467, 43.776]
Solution: | [0.407 0.104 0.395 0.094] |
Teacher: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.
Teacher: Now, understand the problem? Solve this instance: Premise: Mitchell has always been good at basketball.
Initial Context: He decided that he wanted to play football instead.
Original Ending: Mitchell learned everything he could about the new sport. He practiced every day. Now, Mitchell is just as good at football as he was at basketball.
Counterfactual Context: He decided he wanted to take on chess instead.
Student: | Mitchell learned everything he could about the new game. He practiced every day. Now, Mitchell is good at chess and basketball. |
Find the movie name from the given conversation. If the movie name is not found give output as "unknown"
Q: ASSISTANT: what types of movies do u enjoy , USER: I really love action movies. , ASSISTANT: can u name an action movie that u really liked? , USER: One movie I really loved was Venom.
A: Venom
****
Q: ASSISTANT: What type of movies do you enjoy? , USER: comedies, thrillers, suspense , ASSISTANT: What appeals to you with these type of movies? , USER: I like to laugh, I like to be in suspense, and I like thrillers. , ASSISTANT: Is there a specific movie you enjoy from these genres? , USER: The Avengers
A: The Avengers
****
Q: ASSISTANT: What kind of movies do you enjoy and why? , USER: I really like foreign movies, just because it's something unique, and I really like it to focus on the story. You know, reading more on the subtitles. , USER: I really love horror the most followed by drama. , ASSISTANT: Is there a particular film you enjoy? , USER: I really like Trainer Bastion.
A: | Trainer Bastion
****
|
Given the task definition and input, reply with output. Given a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. For commands, 'left' and 'right' are used to denote the direction of an action. opposite turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. Actions and commands do not have quotations in the input and output.
I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_JUMP
| jump around right and jump |
Detailed Instructions: 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.
Q: Fitzbillies is a coffee shop serving French food in a child friendly riverside location with a high price range and high customer rating.
A: | name[Fitzbillies], eatType[coffee shop], food[French], priceRange[more than £30], customer rating[5 out of 5], area[riverside], familyFriendly[yes] |
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".
Japanese: Wikinewsは去る土曜日、オーストラリアのクイーンズランドにあるサンシャイン・コースト・スタジアムで3つのラグビーユニオンの試合を見た。
Thai: ถึงแม้จำนวนผู้สูบบุหรี่จะคงที่หรือลดลงในเขตที่พัฒนาแล้ว แต่มันคงเพิ่มขึ้นในภูมิภาคที่กำลังพัฒนา ซึ่งมีมากกว่าในจำนวนประชากรของโลก และเป็น 84%ของจำนวนผู้สูบบุหรี่ของโลก
No
Japanese: シアトルのハーバービュー医療センターの広報担当者によると、4人目は、29歳の女性で、負傷して病院に運ばれた後で死亡した。また、他の3人は女性1名と男性2名で、全員がひどい火傷によって危険な状態だが生存していた。
Thai: ชายซึ่งอ้างว่าได้ติดระเบิดไว้กับร่างกายของเขาถูกจับกุมตัวหลังจากที่มีการเผชิญหน้ากับเจ้าหน้าที่ตำรวจในเมือง Hertfordshire ประเทศอังกฤษ
No
Japanese: この編集ではまた「サラと彼女の父は、時々午前3時に起き、学校に行く前に大鹿の狩猟をし、家族は定期的に、5キロと10キロのレースを走っている」と書かれた。
Thai: นักปั่นจักรยานชาวนอร์เวย์ Thor Hushovd ได้ปั่นเข้าสู่ชัยชนะในสเตจ 4 สำหรับการแข่งขันตูร์เดอฟร็องส์ 2007 เมื่อวันพุธ
| No
|
Teacher:Read the given sentence and if it is a general advice then indicate via "yes". Otherwise indicate via "no". advice is basically offering suggestions about the best course of action to someone. advice can come in a variety of forms, for example Direct advice and Indirect advice. (1) Direct advice: Using words (e.g., suggest, advice, recommend), verbs (e.g., can, could, should, may), or using questions (e.g., why don't you's, how about, have you thought about). (2) Indirect advice: contains hints from personal experiences with the intention for someone to do the same thing or statements that imply an action should (or should not) be taken.
Teacher: Now, understand the problem? Solve this instance: ( My cats are on Bravecto . )
Student: | no |
Write a fact related to the given fact, based on the given topic word. Note that, your fact should have at least one word in common with the given fact. All facts in this task refer to scientific facts. Your related fact must form a chain with the given fact. Chains form when two facts connect together to produce the third fact. An example of a chain is: "pesticides cause pollution" (given fact) + "pollution can harm animals" (related fact) → "pesticides can harm animals" (connected chain). Avoid creating simple paraphrases of the given fact. While your generated fact should be related to the input fact, they must describe slightly different scientific phenomena. It's okay if your related fact includes some irrelevant information, provided that it has some overlap with the given fact and it contains some words corresponding to the provided topic.
Fact: Stimuli are detected by sensory nerve cells.
Topic: nerve cells detect pain. | When there is a release of pain, the nerve cells in the spinal cord are stimulated. |
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.
One example: password = a
Solution is here: 5
Explanation: Using 5 steps, it can become a strong password
Now, solve this: password = gIypgnBI49
Solution: | 0 |
Given the task definition and input, reply with output. In this task you will be given a string and you should find the longest substring that is a palindrome. A palindrome is a string that is the same backwards as it is forwards. If the shortest possible palindrome is length 1 you should return the first character.
amqaamaaqaaqama
| qaamaaq |
Question: Generate a 5-star review (1 being lowest and 5 being highest) about an app with package giraffine.dimmer.
Answer: | Great app and no crap either |
Given the task definition and input, reply with output. In this task you will be given a string and you should find the longest substring that is a palindrome. A palindrome is a string that is the same backwards as it is forwards. If the shortest possible palindrome is length 1 you should return the first character.
ggggvgvvvggvgvg
| gvvvg |
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].
Problem:[-4, -54, 86, -98, -57]
Solution: | [-29.0, 16.0, -6.0, -77.5] |
Q: 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 |
Context Word: glass.
A: | Glass cups are better than plastic cups because the _ cups are stronger and sturdier. |
Part 1. Definition
Determine if the provided SQL statement properly addresses the given question. Output 1 if the SQL statement is correct and 0 otherwise. 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.
Part 2. Example
Query: SELECT DISTINCT ?x0 WHERE {
?x0 a ns:people.person .
?x0 ns:people.person.spouse_s/ns:people.marriage.spouse|ns:fictional_universe.fictional_character.married_to/ns:fictional_universe.marriage_of_fictional_characters.spouses ?x1 .
?x1 ns:people.person.gender ns:m.05zppz .
?x1 ns:people.person.spouse_s/ns:people.marriage.spouse|ns:fictional_universe.fictional_character.married_to/ns:fictional_universe.marriage_of_fictional_characters.spouses M2 .
FILTER ( ?x0 != ?x1 ) .
FILTER ( ?x1 != M2 )
} Question: Who did M2 's male spouse marry
Answer: 1
Explanation: Query correctly extracts data for male spouse of M2
Part 3. Exercise
Query: SELECT count(*) WHERE {
?x0 ns:people.person.parents|ns:fictional_universe.fictional_character.parents|ns:organization.organization.parent/ns:organization.organization_relationship.parent M0 .
?x1 ns:people.person.children|ns:fictional_universe.fictional_character.children|ns:organization.organization.child/ns:organization.organization_relationship.child ?x2 .
?x2 a ns:film.producer .
M2 ns:influence.influence_node.influenced_by ?x0 .
M2 ns:influence.influence_node.influenced_by ?x1 .
M3 ns:influence.influence_node.influenced_by ?x0 .
M3 ns:influence.influence_node.influenced_by ?x1
} Question: Were M2 and M3 influenced by a child of M0 and influenced by a film producer 's parent
Answer: | 1 |
Given the following Catalan sentence, indicate the name entities (i.e., the real-world objects such as a person, location, organization, etc. that can be denoted with a proper name) such as 'New York Times'. For each words of a named-entity, indicate their type 'LOC' or 'ORG' or 'PER', where 'LOC' indicates a location entity (such as 'New York City', 'ORG' indicates the token of an organization (such as 'Amazon'), 'PER' indicates the tokens of a person entity (such as 'Jeff Bezos'). Named entities with other types should be indicated with 'MISC'. To indicate boundaries of an entity, use IOB (Inside-Output-Begin) prefixes. The B- prefix before a tag indicates that the word is the beginning of a named entity. The I- prefix indicates that the word is inside a bigger chunk. For example, you can break 'New York' to 'New' and 'York.' and tag them as 'B-LOC' and 'I-LOC'. Any token that doesn't belong to a named entity must be tagged with 'O'.
Q: Tot i amb això , ha afegit , actualment l' Agència Catalana de l' Aigua ( ACA ) no té coneixement que hagi entrat en les seves dependències la sol·licitud d' autorització per fer -les , ni per part de l' Ajuntament ni de l' Institut Català del Sòl .
A: | Tot (O) i (O) amb (O) això (O) , (O) ha (O) afegit (O) , (O) actualment (O) l' (O) Agència (B-ORG) Catalana (I-ORG) de (I-ORG) l' (I-ORG) Aigua (I-ORG) ( (O) ACA (B-ORG) ) (O) no (O) té (O) coneixement (O) que (O) hagi (O) entrat (O) en (O) les (O) seves (O) dependències (O) la (O) sol·licitud (O) d' (O) autorització (O) per (O) fer (O) -les (O) , (O) ni (O) per (O) part (O) de (O) l' (O) Ajuntament (B-ORG) ni (O) de (O) l' (O) Institut (B-ORG) Català (I-ORG) del (I-ORG) Sòl (I-ORG) . (O) |
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:
A named third party does receive your unspecified personal information for legal requirements. This applies to a user type outside of our label scheme.
Ex Output:
Generic personal information
Ex Input:
An unnamed third party does receive your financial information for an additional (non-basic) service or feature.
Ex Output:
Financial
Ex Input:
An unnamed third party does do something unspecified with your unspecified personal information for service operations or security.
Ex Output:
| Generic personal information
|
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 Q]: Just do it with bicycles.
[EX A]: no
[EX Q]: I am not a dexfag. Delete this.
[EX A]: yes
[EX Q]: By both sides he means far left, and center left. It's like that scene from Blues Brothers. We have both kinds of music. Country and Western.
[EX A]: | no
|
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.
Q: Progressive multifocal leukoencephalopathy after stem cell transplantation, unsuccessfully treated with cidofovir.
A: | non-adverse drug event |
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".
Q: Japanese: イルハム・アリエフ大統領は、石油による富が地方でのアゼルバイジャンのための軍備拡張競争にお金を出すというアゼリーのルールを主張するために、暴力に訴えることも厭わない、と折に触れて語った。
Thai: เกมส์ถูกเปิดด้วย 4 ประตูในครึ่งแรกสำหรับ Whalers โดยได้สองแต้มจากผู้เล่นปีกขวา Dan Collins
A: | No |
In this task, you are given a string S and a character c separated by a comma. You need to check if the character c is present in S or not. Return 1 if it is present, else return 0.
Q: DwgsdKZrHgmeuJFtFXZR, s
A: 1
****
Q: hgUVcsCempWoijLLdRoZxdToGiVqfb, m
A: 1
****
Q: guIskuyQwlZeyBLhgKaq, z
A: | 0
****
|
Given a hotel review and the corresponding polarity of review (i.e., Negative or Positive) identify if the polarity is correct. Write 'true' if it's correct, 'false' otherwise.
Q: Review: i recently stayed at the amalfi hotel in Chicago and was very disappointed right from the beginning. the girl at the front desk was busy talking to a one of her friends and when i finally did get her to wait on me she was rude and seemed bothered to have to wait on me. the room wasnt at all what i was expecting. it was dingy, dirty, and just seems like an old hotel. just not what i was looking for in a nice hotel. seemed like the quality you'd expect from a cheap motel.
Polarity: Positive
A: | false |
In this task you're given two statements in Marathi. You must judge whether the second sentence is the cause or effect of the first one. The sentences are separated by a newline character. Output either the word 'cause' or 'effect' .
[Q]: त्या माणसाने भाकर बाहेर फेकली.
तो शिळा होता.
[A]: cause
[Q]: त्या माणसाने छत्री बंद केली.
तो इमारतीजवळ आला.
[A]: cause
[Q]: त्या माणसाने मजल्यावर अन्न टाकले.
त्याचा कुत्रा अन्न खाण्यासाठी पळत गेला.
[A]: | effect
|
Part 1. Definition
You are given a statement written in Hindi. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .
Part 2. Example
Statement: सिग्नेचर केल्विन क्लेन अंडरवियर बुटीक, ब्यूनस आयर्स, टोरंटो, मेक्सिको सिटी, <MASK>, ग्लासगो, मेलबोर्न, हांगकांग, लंदन, मैनचेस्टर, न्यूयॉर्क शहर, शंघाई, फ्रैंकफर्ट एम् मेन, सिंगापुर में देखे जा सकते हैं। केल्विन क्लेन अंडरवियर, कार्डिफ़ के सेंट डेविड शॉपिंग सेंटर में भी 2010 में क्रिसमस से पहले एक दुकान खोलने जा रहा है।
Option A: मैनचेस्टर
Option B: मैनचेस्टर
Option C: एडिनबर्ग
Option D: मेलबोर्न
Answer: एडिनबर्ग
Explanation: The most suitable word from the given options to replace the <MASK> token is एडिनबर्ग as the rest places have already been stated in the statement .
Part 3. Exercise
Statement: <MASK> बीबीसी ने टेलीविजन सेवा शुरु की थी। यह विश्व की पहली नियमित हाई डिफनिशन सेवा थी। उस वक्त इसकी 200 लाइनें थी। 1964 में इसका नाम बीबीसी वन किया गया। जो आज भी जारी है।
Option A: 1964
Option B: 1960-
Option C: 1936-
Option D: दूरदर्शक
Answer: | 1936- |
instruction:
In this task, you will be presented with a premise sentence and a hypothesis sentence in Persian. Determine whether the hypothesis sentence entails, contradicts, or is neutral with respect to the given premise sentence. Classify your answers into "Contradiction", "Neutral", or "Entailment".
question:
Premise: من مطمئن نیستم که یکشنبه شب حداقل دما چقدر بود <sep> Hypothesis: نمی دانم شب گذشته چقدر سرد شد.
answer:
Entailment
question:
Premise: گوسفند سنجابی برترین نژاد گوسفند در ایران در تولید پشم است. <sep> Hypothesis: در ایران از گوسفند سنجابی پشم تولید می کنند
answer:
Entailment
question:
Premise: بله ، فکر می کنم آنها کارشان را به خوبی انجام داده اند، اما آنها دقیقاً آن را دنبال نکردند، اما آنها می دانید این کار را تمام و کمال انجام دادند. <sep> Hypothesis: آنها یک نمایش خوب ساخته اند.
answer:
| Entailment
|
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:[-59.651, 201.78, 93.984, -16.438, 8.159, 206.351, -71.563]
Solution: | 51.803 |
You will be given a definition of a task first, then some input of the task.
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.
Film Brain: Luther is sent to get the tree , but there 's only _ one _ left . The one he hit with his car .
Luther: How much is it ?
Scout Leader: $ 75 .
Luther: The sign says $ 15 .
Scout Leader: Supply and demand . The scouts sure could use your $ 75 donation for their camping trip , Mr. Krank .
Film Brain: Stick it up their ass and go somewhere else . I 'm pretty sure that 's not the only tree around . So , Luther buys the tree because he 's an idiot .
Output: | REFERENCE tree |
Given the following Catalan sentence, indicate the name entities (i.e., the real-world objects such as a person, location, organization, etc. that can be denoted with a proper name) such as 'New York Times'. For each words of a named-entity, indicate their type 'LOC' or 'ORG' or 'PER', where 'LOC' indicates a location entity (such as 'New York City', 'ORG' indicates the token of an organization (such as 'Amazon'), 'PER' indicates the tokens of a person entity (such as 'Jeff Bezos'). Named entities with other types should be indicated with 'MISC'. To indicate boundaries of an entity, use IOB (Inside-Output-Begin) prefixes. The B- prefix before a tag indicates that the word is the beginning of a named entity. The I- prefix indicates that the word is inside a bigger chunk. For example, you can break 'New York' to 'New' and 'York.' and tag them as 'B-LOC' and 'I-LOC'. Any token that doesn't belong to a named entity must be tagged with 'O'.
Q: A més , segons SCC , el sector del boví actualment requereix d' uns processos de control i identificació del bestiar ( DIB ) que afegits a altres gestions fan que d' un temps ençà els usuaris es queixin de les llargues cues que s' originen i de les llargues estones d' espera .
A: | A (O) més (O) , (O) segons (O) SCC (B-ORG) , (O) el (O) sector (O) del (O) boví (O) actualment (O) requereix (O) d' (O) uns (O) processos (O) de (O) control (O) i (O) identificació (O) del (O) bestiar (O) ( (O) DIB (B-MISC) ) (O) que (O) afegits (O) a (O) altres (O) gestions (O) fan (O) que (O) d' (O) un (O) temps (O) ençà (O) els (O) usuaris (O) es (O) queixin (O) de (O) les (O) llargues (O) cues (O) que (O) s' (O) originen (O) i (O) de (O) les (O) llargues (O) estones (O) d' (O) espera (O) . (O) |
Teacher: In this task you will be given a string and you should find the longest substring that is a palindrome. A palindrome is a string that is the same backwards as it is forwards. If the shortest possible palindrome is length 1 you should return the first character.
Teacher: Now, understand the problem? If you are still confused, see the following example:
gocogccocco
Solution: gocog
Reason: The substring 'gocog' is the longest possible substring that is also a palindrome. So this is a good example.
Now, solve this instance: acaackccac
Student: | caac |
TASK DEFINITION: In this task you will break down a question into the basic steps required to answer it.
A question decomposition is a numbered list of operations that must be performed to answer the original question. Imagine explaining your question to a friendly droid by listing each action it should take in order for the question to be answered. Each step in our decomposition should refer to either an entity (known or unknown), a propery of an entity or a query operation (count, group, union, etc.)
Here are the list of step templates and their description:
Select: A select step is used to return a set of objects. There are no references to previous steps in a select step. template: Return [attributes]
Filter: A filter step is used to return results from a previous step to which a certain condition applies. template: Return [#step] [condition]
Project: A project step should return certain attributes of the results of a previous step. template: Return [attributes] of [#step]
Aggregate: An aggregate step returns an aggregator function applied on a step's result. template: Return the [aggregator] of [#step].
Group: A group step is an aggregator applied on attributes. template: Return the [aggregator] of [#step] for each [attribute]
Superlative: A superlative step is used to return the result with a highest/lowest attribute among other results. template: Return [#step1] [where] [#step2] [is] [highest / lowest]
Comparative: A comparative step is used when we need to compare an attribute with a number to filter results. template: Return [#step1] [where] [#step2] [comparator] [number]
Union: A union step is used to return results of two steps together. template: Return [#step1] [or / ,] [#step2]
Intersection: An intersection step returns the result that two steps have in common. template: Return [attribute] of both [#step1] and [#step2]
Discard: A discard step returns result of a step and excludes result of another step from it. template: Return [#step1] besides [#step2]
Sort: A sort returns result of another step in a specific order. template: Return [#step1] [ordered / sorted by] [#step2]
Is true: An is true step checks a condition on another result and returns a true or false. template: Return [is / if] [condition]
Arithmetic: An arithmatic step operates an arithmatic operation on one or more steps. template: Return the [arithmetic op.] of [#step1] [and] [#step2].
PROBLEM: question: If an image shows a single white roll on a wood surface.
SOLUTION: #1 return roll
#2 return #1 that is white
#3 return surface
#4 return #3 that is wood
#5 return #2 that is on #4
#6 return images
#7 return number of #5 for each #6
#8 return #6 where #7 is equal to one
#9 return number of #8
#10 return if #9 is at least one
PROBLEM: question: How many field goals did Elam kick in the second half?
SOLUTION: #1 return Elam
#2 return field goals #1 did kick
#3 return #2 in the second half
#4 return the number of #3
PROBLEM: question: Show the country name and capital of all countries.
SOLUTION: | #1 return countries
#2 return names of #1
#3 return capitals of #1
#4 return #2 , #3
|
Instructions: In this task, you will be presented with a question in Dutch language, and you have to write the person names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Phrase used for the person name - PER. There can be instances with no person name entity, then return 'None'.
Input: In dezelfde periode was Larmuseau ook lid van de interkabinettengroep rond ABC Containerline , die specifiek was opgericht om de fiscale problemen op te lossen die opdoken in het kader van de voorgespiegelde overname van de rederij door de Amerikaanse oplichter Gary Blonder .
Output: | Larmuseau: B-PER, Gary: B-PER, Blonder: I-PER |
Given the task definition, example input & output, solve the new input case.
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.
Example: [2,5,1,4],[2,5,8,4,2,0]
Output: [2,4,5]
The elements 2,4, and 5 are in both lists. This is a good example.
New input case for you: [2, 7, 8, 10, 7, 10, 7, 10, 10] , [3, 5, 8, 5, 7, 9, 3, 4, 10]
Output: | [7, 8, 10] |
Given a prompt and two completions from a language model, select the completion that is the most fluent with respect to continuing the prompt. Fluency is defined by coherency and ease of understanding, not necessarily grammatical correctness. Generate either Completion A or Completion B.
[Q]: Prompt: Vic is fucking my old bitch, Nunu. She's acting like she didn't fuck
Completion A: you, like you were your shit, like you were like a fucktoy or something. And she's the bitch I'm gonna be
Completion B: her stepfather either. And then she starts screaming at the top of her lungs that she's going to sue for $10 million. How is tha
[A]: Completion B
[Q]: Prompt: Don't let me find out that bitches on Twitter are trash
Completion A: V p a me the Gods had more convert rain didn't BF3 2014 win at Gamers 1 we're … Sharld Price
Completion B: ! You‖re right, it's not worth that much. I'm sure you'd find a much more effective way to engage wit
[A]: Completion B
[Q]: Prompt: Sometimes the shit you fuck with, is just
Completion A: about all you need, right there on the page so you can get high as fuck with everyone and everyone with a free speech on this place.
Completion B: shit. And the stuff you do is not only fuck, but also fuck shit, or at least fuck shit like that. Fuck your ow
[A]: | Completion A
|
Detailed Instructions: You are given a short text as a title. Your task is to generate a poem as output that is related to the given title and should feel like written by kids. The output should be a run-on sentence (two or more complete sentences connected without any punctuation). The poem should not be too long or too complex, because it should feel like it is written by younger person without high level of literature education.
Problem:Rats nest
Solution: | when i wake up one morning a rat be on my head i ask what be you do there it just look at me and say''well i be just squeking around and happen to step on your bed. i go out to the kitchen and there stand my mom who say why do you have a rat nest on your head uh well you have good go out and grab a comb to make sure that rat be dead |
Q: Turn the given fact into a question by a simple rearrangement of words. This typically involves replacing some part of the given fact with a WH word. For example, replacing the subject of the provided fact with the word "what" can form a valid question. Don't be creative! You just need to rearrange the words to turn the fact into a question - easy! Don't just randomly remove a word from the given fact to form a question. Remember that your question must evaluate scientific understanding. Pick a word or a phrase in the given fact to be the correct answer, then make the rest of the question. You can also form a question without any WH words. For example, "A radio converts electricity into?"
Fact: A balance is used for measuring the aspect of an object that is measured in kilograms.
A: | Which measuring unit might be used when using a balance? |
In this task, you are given a country name and you need to answer with the government type of the country, as of the year 2015. The following are possible government types that are considered valid answers: Republic, Parliamentary Coprincipality, Federal Republic, Monarchy, Islamic Republic, Constitutional Monarchy, Parlementary Monarchy, Federation.
Let me give you an example: Angola
The answer to this example can be: Republic
Here is why: Republic is the government type of the country called Angola.
OK. solve this:
Italy
Answer: | Republic |
Definition: 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.
Input: Command: eq { hop { nth_argmax { all_rows ; attendance ; 2 } ; site } ; ben hill griffin stadium gainesville , fl }, interpretation: select the row whose attendance record of all rows is 2nd maximum . the site record of this row is ben hill griffin stadium gainesville , fl .
Output: | yes |
Given an adjective, generate its antonym. An antonym of a word is a word opposite in meaning to it.
trinucleate | mononuclear |
You will be given two sentences. One of them is created by paraphrasing the original one, with changes on an aspect, or using synonyms. Your task is to decide what is the difference between two sentences. Types of change are explained below:
Tense: The verbs in the sentence are changed in tense.
Number: Plural nouns, verbs and pronouns are changed into single ones or the other way around.
Voice: If the verbs are in active voice, they're changed to passive or the other way around.
Adverb: The paraphrase has one adverb or more than the original sentence.
Gender: The paraphrase differs from the original sentence in the gender of the names and pronouns.
Synonym: Some words or phrases of the original sentence are replaced with synonym words or phrases. Changes in the names of people are also considered a synonym change. Classify your answers into Tense, Number, Voice, Adverb, Gender, and Synonym.
--------
Question: original sentence: It was a summer afternoon , and the dog was sitting in the middle of the lawn . After a while , it got up and moved to a spot under the tree , because it was hot . paraphrase: it was a summer afternoon , and the canine was sitting in the middle of the lawn . after a while , it got up and moved to a spot under the bush , because it was hot .
Answer: Synonym
Question: original sentence: In the storm , the tree fell down and crashed through the roof of my house . Now , I have to get it repaired . paraphrase: in the storm , the willow fell down and crashed through the ceiling of my house . now , i have to get it repaired .
Answer: Synonym
Question: original sentence: John hired Bill to take care of him . paraphrase: John and Peter hired Bill and Steven to take care of them .
Answer: | Number
|
Teacher: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.
Teacher: Now, understand the problem? Solve this instance: ['W', 'w', 'z', '9', 'N']
Student: | [['W', 'w', 'z', '9'], ['W', 'w', 'z', 'N'], ['W', 'w', '9', 'N'], ['W', 'z', '9', 'N'], ['w', 'z', '9', 'N']] |
Teacher: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.
Teacher: Now, understand the problem? Solve this instance: The Golden Palace is a coffee shop for dinner. We make hamburgers. We are near the River at City Centre. Join us.
Student: | name[The Golden Palace], eatType[coffee shop], food[Fast food], priceRange[high], customer rating[1 out of 5], area[riverside] |
TASK DEFINITION: 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.
PROBLEM: ['U', 'Z', 'i']
SOLUTION: [['U', 'Z'], ['U', 'i'], ['Z', 'i']]
PROBLEM: ['4', 'k', 'e']
SOLUTION: [['4', 'k'], ['4', 'e'], ['k', 'e']]
PROBLEM: ['0', 'E', 'S']
SOLUTION: | [['0', 'E'], ['0', 'S'], ['E', 'S']]
|
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.
[ 9.387 74.08 -42.656 45.943] | 74.08 |
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.
[24, -2, 79, 17, -71, -13, 25, 43] | 1 |
Part 1. Definition
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.
Part 2. Example
“Wo ọmọọ̀ mi dè mí”: ó ń lo kíjìpá mẹ́ta gbó; mélòó ni ọlọ́mọọ́ máa lò gbó?
Answer: “Look after the child for me”: she wears three durable hand-loom wrappers to tatters; how many would the mother of the child herself wear out?
Explanation: The Yoruba sentence is properly translated to the English language as both the sentences convey the same meaning and both the sentences are in sentence case and it preserves the punctuation marks as well.
Part 3. Exercise
Àjọ kan tí wọ́n ń pè ní Munich Documentation Centre for the History of National Socialism ṣètò àkànṣe kan ní September 26, 2018, sí January 6, 2019, káwọn èèyàn lè mọ ohun ti ìjọba Násì fojú àwọn Ẹlẹ́rìí Jèhófà rí lásìkò tí wọ́n ń ṣàkóso.
Answer: | From September 26, 2018, to January 6, 2019, the Munich Documentation Centre for the History of National Socialism hosted a special exhibit designed to raise the public’s awareness of the experiences of Jehovah’s Witnesses during the Nazi era. |
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: [ 16.567 15.26 -92.255 44.9 6.102 8.066 82.396]
Output: -92.255
Input: Consider Input: [-66.39 -11.603 -0.203 50.595 84.817]
Output: 84.817
Input: Consider Input: [-99.959 -12.362 65.474 -97.313]
| Output: -99.959
|
Given the task definition and input, reply with output. 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: hedgehog
Entity 2: head
| yes |
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 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.
round_eq { sum { all_rows ; casinos } ; 217 }
Solution: aggregation
Why? In this example sum returns the sum of the values in all of the casinos rows. Hence, aggregation is right category.
New input: eq { count { filter_eq { all_rows ; competition ; friendly } } ; 4 }
Solution: | count |
Given the task definition and input, reply with output. Indicate if the following Polish tweet contains cyber-bullying content with 'Yes'; otherwise, respond with 'No'.
Tweet: Bracia Paixao strzelali gole Jagiellonii w pięciu ostatnich meczach z Jagiellonią i sześciu z ostatnich siedmiu. , Question: Is the tweet free of any cyberbullying (harmful) content?
| Yes |
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:7885 sottrazione 2030 sottrazione 6805 sottrazione 6493 aggiunta 8718
Solution: | 1275 |
You will be given a definition of a task first, then some input of the task.
In this task you're given two statements in Marathi. You must judge whether the second sentence is the cause or effect of the first one. The sentences are separated by a newline character. Output either the word 'cause' or 'effect' .
मी गरम सूपमध्ये बर्फाचे तुकडे ठेवले.
सूप थंड झाला.
Output: | effect |
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: BACKGROUND: Reproductive endocrine disorders characterized by menstrual disorders, polycystic ovaries, and hyperandrogenism seem to be common among women treated with sodium valproate for epilepsy.
Student: | adverse drug event |
TASK DEFINITION: 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
PROBLEM: 1709 # 2270 # 1077 # 9681
SOLUTION: -11319
PROBLEM: 126 @ 8943 @ 2476 # 7766 @ 2271 # 7213 @ 6602 # 8086 @ 2129
SOLUTION: -518
PROBLEM: 7589 @ 4863 @ 7930 @ 6858 @ 7606 # 3193 # 3679 # 2569 # 1394
SOLUTION: | 24011
|
Subsets and Splits