uniq_id stringlengths 36 36 | messages stringlengths 2.65k 180k | answers listlengths 1 1 | num_tokens int64 507 32.7k | task stringclasses 7
values |
|---|---|---|---|---|
792697f2-91cb-4441-9378-9ac9c81894dd | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the discussion on future directions\n\nProfessor D: OK .\nPhD A: Mike . Mike - one ?\nPhD B: Ah .\nProfessor D: We 're on ? Yes , please . I mean , we 're testing noise robustness but let 's not get silly . OK , so , uh , yo... | [
"The team discussed testing a multi-band approach that is more resistance to noise. The professor thought that it many not be a bad idea to put together several MLP's to improve performance. The team also thought that there might be problems with the pronunciation models."
] | 18,386 | qmsum |
b6ee5980-924b-4e6c-90d5-b12a90ec8120 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What did Julie Morgan think of the monitoring system for the vulnerable children when discussing the priority to care for them?\n\nLynne Neagle AM: Good afternoon. Can I welcome Members to the virtual meeting of the Children, Young Pe... | [
"When discussing the priority to take care of the vulnerable children, Julie Morgan mentioned that they would set out an expanded definition for the local authorities to have a clear idea about who and where to lay the stress. What's more, according to her claim, they had done a good job to guarantee that the child... | 13,008 | qmsum |
cd86815b-836c-416e-bf36-7a3678ca4f58 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the discussion about product quotation.\n\nProject Manager: Uh fourth meeting . {vocalsound}\nUser Interface: We have to do what ?\nProject Manager: Some extra deciding .\nIndustrial Designer: {vocalsound} W what ? Alri alri... | [
"When evaluating the cost of the product, the group discussed some details of the components and made some adjustment on the chip, exterior cover material, curve, button and LCD screen. Then they agreed that it could be better changing the titanium to hard a hard kind of plastic looking like titanium than losing th... | 15,252 | qmsum |
f2612df0-4b7c-4a90-aadd-da90e5f1b5b3 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the discussion about interface concept design.\n\nProject Manager: Okay . {vocalsound} Well , let's start . What are we doing ? Oops . {vocalsound}\nUser Interface: Hmm .\nIndustrial Designer: Ah , pinball .\nProject Manager... | [
"The team believed that there were always large and many buttons on the standard remote control. To design its unique device, they decided on a pure color one with arrows to eliminate the number of buttons used. They also planned to incorporate the company logo. Moreover, User Interface suggested a set of buttons w... | 8,199 | qmsum |
f7ebc678-0434-46cb-9692-40e26fb52165 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the discussion about the results from the experiments\n\nProfessor D: OK .\nPhD A: Mike . Mike - one ?\nPhD B: Ah .\nProfessor D: We 're on ? Yes , please . I mean , we 're testing noise robustness but let 's not get silly .... | [
"Last run of experiments showed that adding more languages was still severely harming model performance. They noted that normalization of any kind has a good effect on the model, whereas MSG does nothing."
] | 18,389 | qmsum |
015cee2a-4aa9-4df9-854d-04a41d7be642 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the meeting\n\nProfessor D: OK .\nPhD A: Mike . Mike - one ?\nPhD B: Ah .\nProfessor D: We 're on ? Yes , please . I mean , we 're testing noise robustness but let 's not get silly . OK , so , uh , you 've got some , uh , Xe... | [
"The participants went over the results of the most recent experiments, discussing future directions to take. Adding in more languages was still decreasing model performance. The best network consisted of the TIMIT and noise. The team thought that they should try to reduce their dependence on noise in the data. The... | 18,383 | qmsum |
4a3a7072-4c9e-4e6b-923f-0b6b7d242007 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the discussion on detecting important linguistic features\n\nProfessor A: Am I on ? I guess so . Radio two . Hmm . Radio two .\nGrad E: Hello ?\nProfessor A: Wow .\nGrad E: Mm - hmm . Hi ?\nPhD B: Blow into it , it works re... | [
"The team wanted to understand how they could combine different linguistic features to make a more robust recognition model. They were running experiments to figure out what the good features were. The team also entertained the possibility of clustering them, which would add to the robustness."
] | 11,226 | qmsum |
4a7d214d-ec1b-4efa-8b4e-48fca3528402 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Why did Industrial Designer put forward that the appearance design should be paid due attention when discussing the user interface?\n\nIndustrial Designer: {vocalsound}\nMarketing: Are you sure I got it all {disfmarker} head's kinda s... | [
"Industrial Designer was unsatisfied with the existing remote controls, for that they are seemingly cheap and of low quality. Thus the Industrial Designer intended to make it nice and slick, maybe something with multi plates."
] | 8,087 | qmsum |
5f12c48e-b954-4446-b282-4dafe77e715d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize Kirsty Williams' opinion on the current geographic spread of provision when discussing the decision of not accrediting the University of South Wales with the ability to deliver teacher training.\n\nLynne Neagle AM: Good morn... | [
"Kirsty Williams said there was a significant geographic spread with their current providers currently. They thought for some students, accessibility was an issue, and that was why they were responding with their part-time PGCE route, which actually would be located neutral. Therefore, if geographical disadvantages... | 17,806 | qmsum |
990be9e9-900a-406f-b28b-a0ca4554dce0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What did D think about the experimental setup of the computer navigation system?\n\nGrad E: I guess .\nGrad A: OK , we 're on . So just make sure that th your wireless mike is on , if you 're wearing a wireless .\nGrad E: Check one . ... | [
"D wanted to know if the videos for the navigation system would be recorded from a first person perspective. D was also trying to understand how ambitious the system was. D learned that the goal was to understand how people reacted and talked in such a scenario. D provided some information about potential candidate... | 18,558 | qmsum |
aaa435de-775c-4140-9e19-e14c2a30ac09 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the meeting\n\nGrad A: OK , we 're on .\nProfessor B: Yeah .\nGrad A: So , I think this is gonna be a pretty short meeting because I have four agenda items , three of them were requested by Jane who is not gonna be at the me... | [
"The meeting concerned mostly status updates and logistical affairs. The participants learned that the transcription status was good. The progress on the DARPA demo was also good, except the interface did not look as pretty as they had wanted to. The storage disks, which they had been waiting for, had finally arriv... | 16,921 | qmsum |
cf5f2bb6-e2d7-45e4-88b8-d572fde65a5a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize Eluned Morgan's opinion on the pay dispute situation.\n\nLynne Neagle AM: Good morning, everyone. Welcome to the Children, Young People and Education Committee. We've received no apologies, although Dawn Bowden is running la... | [
"Eluned Morgan agreed with Dawn Bowden that this was about ColegauCymru's negotiation. They would keep a close eye on this situation, but they would wait for the outcome of the negotiations of ColegauCymru before they take any serious steps. They had listened and spoken to ColegauCymru and were aware of what the un... | 17,784 | qmsum |
deaac95d-a387-4809-acce-8bb1b1f741a3 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the presentation on evaluation criteria.\n\nIndustrial Designer: {vocalsound} I'm proud of it . {vocalsound}\nUser Interface: {vocalsound}\nProject Manager: Okay . This is our final meeting , the detailed design meeting . An... | [
"The group gave a high score in terms of a fashion look, the ease of use, the locator, the scroll wheel, the LCD screen as well as the voice recognition technology. They also calculated the average overall score was six point five. The group agreed that the assessment was very good."
] | 12,958 | qmsum |
0a1ebb16-d3a6-4619-9f1f-79aa1fa7fbbb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the questioning about the reports on long-term care facilities?\n\nThe Chair (Hon. Anthony Rota (NipissingTimiskaming, Lib.)): I call this meeting to order. Welcome to the 12th meeting of the House of Commons Special Committe... | [
"The opposition party questioned that the report was delayed in issuing by the government and was not acted upon. The minister answered that the report was done and given up through the chain of command, and once the government received this report, it was forwarded to the appropriate authorities. The minister deni... | 25,568 | qmsum |
45ee59b0-ae28-43bf-b196-583f70e032f5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What did Vaughan Gething think of the mental health recovery plan when talking about the ways of continuing mental health service during the lockdown?\n\nLynne Neagle AM: Good afternoon. Can I welcome Members to the virtual meeting of... | [
"When it comes to continuing mental health service during the lockdown, Vaughan Gething insisted that it was of great necessity to carry out a mental health recovery plan that with such a system, government can ensure the children could enjoy a healthy mental state during the school lockdown. However, at present th... | 13,012 | qmsum |
9bf84f40-966e-424b-9888-586207dc9376 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What did Bains say about the threshold for the wage subsidy program and loan refinancing?\n\nThe Chair (Hon. Anthony Rota (NipissingTimiskaming, Lib.)): I call the meeting to order. Welcome to the seventh meeting of the Special Commit... | [
"Bains said that the threshold for the program had been lowered to a 15% decline in revenue from a 30% decline. Businesses will also be able to compare losses to more recent time periods due to greater flexibility. Bain clarified that the government is listening to businesses and recognizes its need to be agile."
] | 30,314 | qmsum |
e52faf17-fce5-473a-97f0-aaaa510bae9f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the discussion about project finance.\n\nIndustrial Designer: {vocalsound} I'm proud of it . {vocalsound}\nUser Interface: {vocalsound}\nProject Manager: Okay . This is our final meeting , the detailed design meeting . And a... | [
"The production cost was 12.5 Euros. So, the group decided to have one simple battery, no kinetic energy, no solar, one advanced chip on print, one sample speaker, one single-curved surface which can be folded, push-buttons, the scroll wheel, the LCD display. And they decided to give up the sample sensor as well as... | 12,958 | qmsum |
ec49deb2-33f9-4366-a727-1630e7b6b1ad | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What did the marketing learn about the trend?\n\nProject Manager: Okay , so now we are on the conceptual design meeting . {vocalsound} Uh y getting close to the last\nMarketing: Mm-hmm .\nProject Manager: is the penultim meeting . {vo... | [
"The marketing found that trends were quite the same in many areas. Take this year's fruit and vegetable as an example, it applies to everything from clothing to furniture, which meant it was quite general. It might be surprising that people liked products that looked natural and round rather than some futuristic r... | 10,056 | qmsum |
30b0ad1f-fec8-4e3d-a81e-d8b72d7eb31f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is Industrial Designer's presentation mainly about?\n\nProject Manager: Okay . Uh door is closed . {vocalsound}\nIndustrial Designer: {vocalsound}\nProject Manager: Well , let's begin . Because if we have as much time as the last... | [
"He talks about something on the components design after having put up the specification properties. As for materials, he used to suggest using hard plastic in order to make the control hard and solid, but at this conference, he thinks that their target audience, young people, love soft colors and materials, like r... | 15,623 | qmsum |
5001036d-1b39-4a2f-a817-5432a442673c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What demos would the system be involved in?\n\nGrad B: \nGrad D: How many batteries do you go through ?\nGrad B: Thank you .\nProfessor C: Alright .\nPhD A: Sure .\nProfessor C: Good . Yeah . OK so , let 's get started . Nancy said sh... | [
"The final english SmartKom demo will be presented to the whole institute once the system is de-bugged and stabilised."
] | 15,552 | qmsum |
65e68f0b-df97-4468-bee9-c0b5d49f534d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize their discussions on university mergers.\n\nLynne Neagle AM: Good morning, everyone. Welcome to the Children, Young People and Education Committee. We've received no apologies, although Dawn Bowden is running late. I'll take... | [
"Kirsty Williams firstly proposed that the main goal he would like to pursue was a healthy, strong and sustainable HE sector. They did not pursue or urge a policy of mergers, but they welcomed the mergers, if this was beneficial for individual institutions. Hefin David proposed that was in contrast with the predece... | 17,780 | qmsum |
85e31ed7-cced-4c5d-9325-562d2e86d018 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How did the Prime Minister debate about the delaying of the government's response towards Covid-19?\n\nThe Chair (Hon. Anthony Rota (NipissingTimiskaming, Lib.)): I call this meeting to order. Welcome to the 12th meeting of the House ... | [
"In response to the opposition party, the Prime Minister answered that the government rolled out the Canada emergency response benefit extremely quickly, and they had been helping the small businesses with the Canada emergency business account. The opposition party was not very satisfied because he thought that the... | 25,575 | qmsum |
9ac6336c-a590-43e1-81de-4acbb94413f2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What did the group talk about the touch screen under the limitation of the budget?\n\nMarketing: {vocalsound} That went well , thank you .\nProject Manager: That's great .\nIndustrial Designer: {vocalsound} 'Kay .\nMarketing: Perfect ... | [
"The group found that if they would use the touch screen as well as the voice recognition technique, the cost would up to 17 euros. On the other hand, in order to guarantee the one hundred percent profit, the price would be more than 30, which would risk losing potential consumers. Provided that they would control ... | 10,187 | qmsum |
b6492475-9ffe-40aa-b214-200ba4e6f6ba | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What did the professor think about scheduling meetings going forward?\n\nGrad A: OK , we 're on .\nProfessor B: Yeah .\nGrad A: So , I think this is gonna be a pretty short meeting because I have four agenda items , three of them were... | [
"The professor polled the group on how many people would not be interested in meetings on recognition. He thought that they should at least try the smaller meetings and see what happens."
] | 16,926 | qmsum |
0a7ebdca-32ab-4413-8f3f-7bb5320c40aa | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What did Huw Irranca-Davies think about the pilots in Cardiff and Newport?\n\nLynne Neagle AM: Good morning, everyone. Welcome to the Children, Young People and Education Committee. We've received apologies for absence from Julie Morg... | [
"New pilots in Cardiff and Newport would start in September. This was to learn the experiences of the high-cost areas. If it was shown that the rate in these areas was more expensive, then the team would come back and discuss it with the committee. But Huw Irranca-Davies emphasized that the project should start fir... | 16,233 | qmsum |
1c27baae-d0a4-42cd-92b4-b41c374fdade | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What did PhD C think about the signal to noise ratio?\n\nProfessor B: I think for two years we were two months , uh , away from being done .\nPhD A: And what was that , Morgan ? What project ?\nProfessor B: Uh , the , uh , TORRENT chi... | [
"PhD C was skeptical of why the signal was louder after processing. PhD C suggested that the system is not too dependent on the signal level, agreeing with the professor that improvement in the model was more likely dependent on the ratio."
] | 15,814 | qmsum |
87fadc7a-1e6d-47dd-bec1-c4722167d979 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What did the professor think about improving the back recognizer for the Aurora task?\n\nProfessor A: Am I on ? I guess so . Radio two . Hmm . Radio two .\nGrad E: Hello ?\nProfessor A: Wow .\nGrad E: Mm - hmm . Hi ?\nPhD B: Blow int... | [
"The Professor thought that the experiments were pretty simple, so computational power was not really a problem. He also thought that it would be okay to increase the states from six to nine."
] | 11,230 | qmsum |
b79d5835-3f94-4566-b16c-668510a75d52 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What did the group talk about the functions and buttons of the remote control?\n\nProject Manager: All set ? Okay . Cool . Right . So um basically I'm just gonna go over real quickly um some news I've just got from the board on how we... | [
"To cater to the potential consumers aged under 35, the group decided to use voice control to locate the remote. During their discussion of the voice control technique on the remote control, they also took into consideration several detailed problems. They planned to set the control range within 200 feet and arrang... | 6,694 | qmsum |
c5e23744-254c-40ef-907b-cefd95e21e79 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the government's policy towards the university's estates strategy?\n\nLynne Neagle AM: Good morning, everyone. Welcome to the Children, Young People and Education Committee. We've received apologies for absence from Suzy Davi... | [
"Dr David Blaney introduced that there was proper governance oversight since the estates strategies that institutions operate were overseen by either the full governing body or relevant sub-committees in respect of every institution. The government was content with the fact that the governance machinery within the ... | 12,775 | qmsum |
ef223342-4964-4c27-be56-4b240227bc26 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was said on speech overlap?\n\nProfessor E: So . OK . Doesn't look like it crashed . That 's great .\nGrad G: So I think maybe what 's causing it to crash is I keep starting it and then stopping it to see if it 's working . And s... | [
"Efforts by speaker mn005 are in progress to detect overlapping speech. For a single transcribed meeting, speaker mn005 reported approximately 300 cases of overlap. Future work will involve manually deriving time marks from sections of overlapping speech for the same meeting, and then experimenting with different m... | 26,110 | qmsum |
f765c630-886d-4042-a46b-3085af8e11ab | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the group's plan of their marketing strategy.\n\nMarketing: {gap}\nProject Manager: {gap} {vocalsound}\nMarketing: I dunno . {vocalsound} Throwing away my toothpick .\nUser Interface: Hi there .\nProject Manager: Yo . Ow .\n... | [
"They want to keep the cost under 12.50 euros by controlling the materials, and they want to sell them internationally for 25 euros, with a target of 50 million euros worldwide. So they wanted the remote to be compatible with most TVS in the world, or at least all the TVS they make."
] | 9,267 | qmsum |
ffa764a7-03ac-4dc0-a2b6-7544611907fa | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What did Vaughan Gething think of the perinatal mental health service when discussing the long-term special care for the pregnant women?\n\nLynne Neagle AM: Good afternoon. Can I welcome Members to the virtual meeting of the Children,... | [
"Besides the crisis care, Vaughan Gething also claimed that they did not stop the perinatal mental health service either. However, there were still some problems. For example, because of the shut down of many public services, there might be not enough inpatient care for the pregnant, and less women were willing to ... | 13,012 | qmsum |
0ec34406-2554-4449-9558-6b1b720da706 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Why did the Industrial Design disagree with the User Interface when discussing the shape of the remote control?\n\nMarketing: {vocalsound} That went well , thank you .\nProject Manager: That's great .\nIndustrial Designer: {vocalsound... | [
"The User Interface proposed to give up the idea of a hand-held model and give its way to the voice recognition system, while the Industrial Design thought it would be necessary for remote control to be able to be held in hand. Industrial Design believed that not all the people would always use the voice recognitio... | 10,190 | qmsum |
77fbe017-d483-4b79-9d0a-6d96578ff1fc | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the controversy about China hoarding PPE amid the pandemic?\n\nThe Chair (Hon. Anthony Rota (NipissingTimiskaming, Lib.)): I call this meeting to order. Welcome to the 12th meeting of the House of Commons Special Committee on... | [
"The opposition party claimed that China was procuring and hoarding PPE during January. And in April, the minister stated there were not enough supplies in the national emergency stockpile. The opposition party was triggered by the fact that the minister approved a donation of 16 tonnes of PPE for China on January ... | 25,569 | qmsum |
850a44ce-ea66-4b3a-b5d9-90a2b61a4cd9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the Project Manager's perspective on the prototype.\n\nProject Manager: Uh fourth meeting . {vocalsound}\nUser Interface: We have to do what ?\nProject Manager: Some extra deciding .\nIndustrial Designer: {vocalsound} W what... | [
"The Project Manager thought the prototype was basically the same with the former one, and the thickness was not suitable for the target customers. Then the LCD screen might be covered when held by hands, so the users couldn't figure out what happened on the screen. Therefore from this perspective the screen was to... | 15,255 | qmsum |
8a9a336c-e8e0-4a04-8381-a4cb0d37fb0d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is User Interface's presentation mainly about?\n\nProject Manager: Okay . Uh door is closed . {vocalsound}\nIndustrial Designer: {vocalsound}\nProject Manager: Well , let's begin . Because if we have as much time as the last uh m... | [
"User Interface talked about the method of including the buttons and the implementation of LCD screens. And he mentioned there are new developments in speech recognition systems as they are already being used on uh coffee machines; and since they're cheap, so he thinks they could use them now, as a small gimmick. A... | 15,623 | qmsum |
a8109de2-cc2b-4672-bd97-ede1dbca515f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the discussion about product evaluation.\n\nProject Manager: Mm .\nMarketing: So ,\nProject Manager: So , uh now {vocalsound}\nMarketing: Hi Christa . {vocalsound}\nProject Manager: it's the {disfmarker} {vocalsound} Hi Samm... | [
"The marketing thought they needed to evaluate whether it made sense to do the project and whether the product could fulfil their requirement. So the group started to judge the design on a scale of one to seven, one being true and seven being false. The criteria were fanciness, technology, robustness, usefulness, s... | 13,316 | qmsum |
aefaaec3-41ad-49b6-ad3c-c49521a68aab | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How did Kirsty Williams respond to university mergers?\n\nLynne Neagle AM: Good morning, everyone. Welcome to the Children, Young People and Education Committee. We've received no apologies, although Dawn Bowden is running late. I'll ... | [
"Kirsty Williams said he was in favor of a healthy, strong and sustainable HE sector. If individual institutions wish to collaborate, that was a matter for themselves. They did not pursue or urge a policy of mergers, but if individual institutions felt that was of benefit to them and their students, they would have... | 17,781 | qmsum |
ca7ccc36-4356-4480-8bc1-468e272addce | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was decided on the microphone procedures?\n\nGrad F: Test .\nPostdoc G: OK .\nProfessor B: Let 's see , I should be Two .\nPhD D: Up high {disfmarker}\nGrad E: As close to your mouth as you can get it .\nProfessor B: La\nPhD D: h... | [
"Following close-talking microphone recognition procedures, it was decided that data from the far-field microphones (or PZMs) should be tested on the recognizer as soon as possible. Speaker mn017 will compare close-talking microphone recognition results with those obtained for downsampled data. The SRI recognizer w... | 16,843 | qmsum |
4d2bfa71-5d08-4ce9-b963-79d1f61b25e3 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the presentations on working design, technical functions, functional requirements.\n\nProject Manager: All hooked up . {vocalsound} Okay , so now we are here at the functional design meeting . Um {vocalsound} hopefully this ... | [
"Firstly, Industrial Designer presented on working design, identifying a few basic components of the remote. From the functional design perspective, Industrial Designer introduced what exactly the components were and how they worked with each other. Next, User Interface presented on technical functions design and p... | 10,869 | qmsum |
7fe858bb-ec17-4a91-abae-0d1890599695 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What did Bains say about the arts, culture, and tourism industry?\n\nThe Chair (Hon. Anthony Rota (NipissingTimiskaming, Lib.)): I call the meeting to order. Welcome to the seventh meeting of the Special Committee on the COVID-19 Pand... | [
"Bains claimed that the government was aware of these issues and had allocated $500 million to arts and culture organizations. Bains also explained that while pandemic control efforts were affecting these industries adversely, Canadians' health and safety remained the government's priority."
] | 30,311 | qmsum |
8edae6af-3bb5-4eef-8f41-6aec49240855 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is Marketing's presentation mainly about?\n\nProject Manager: Okay . Uh door is closed . {vocalsound}\nIndustrial Designer: {vocalsound}\nProject Manager: Well , let's begin . Because if we have as much time as the last uh meetin... | [
"Marketing talks about the adoption of some latest trends and latest fashion updates on the remote control. She thought it important that the control looks fancy for targeted young users, like having the LCD screen, vivid colors, and cool shape, and the last model of the company is comparatively functional."
] | 15,622 | qmsum |
953d6edc-2fbc-4b4f-b31d-b3c2e98507d1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the discussion on storage disks and computer connections\n\nGrad A: OK , we 're on .\nProfessor B: Yeah .\nGrad A: So , I think this is gonna be a pretty short meeting because I have four agenda items , three of them were re... | [
"The participants learned that the storage disks had eventually arrived. They were waiting on the disks to be installed. Grad E volunteered storage space on their own computer for the meantime. The meetings were around 1.5 gigs uncompressed and .5 gigs compressed. So, the group needed substantial space. The profess... | 16,927 | qmsum |
aab08b89-94b8-473e-b2df-fbaab5cee358 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the brief presentations on personal ideas towards the design.\n\nProject Manager: All set ? Okay . Cool . Right . So um basically I'm just gonna go over real quickly um some news I've just got from the board on how we're sup... | [
"Except for the Project Manager, the other three members of the group all did a presentation to show their research findings on the television remote. The Industrial Designer suggested not to use too much metal in case they would disturb the signals. After him, the User Interface focused on the functions that he pr... | 6,692 | qmsum |
d7b04e9c-cfd4-44be-9d19-a8279beb7e0c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Summarize the whole meeting.\n\nThe Chair (Hon. Anthony Rota (NipissingTimiskaming, Lib.)): I call the meeting to order. Welcome to the seventh meeting of the Special Committee on the COVID-19 Pandemic. Please note that today's procee... | [
"The participants discussed the government's response to the coronavirus. Participants expressed concern over a variety of matters that ranged from welfare transfers to protecting small businesses. The Prime Minister was questioned on alleged fraud in the distribution of pandemic relief funds. The participants were... | 30,303 | qmsum |
f6b33356-ddbc-4cd7-8567-af0b915f79f1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the general discussion?\n\nGrad F: Test .\nPostdoc G: OK .\nProfessor B: Let 's see , I should be Two .\nPhD D: Up high {disfmarker}\nGrad E: As close to your mouth as you can get it .\nProfessor B: La\nPhD D: high as you can... | [
"The group discussed recognition results generated for 20 minutes of close-talking microphone data. Recognition performance was very good, indicating promising results for forced alignment procedures and the ability to analyze other important signal information, e.g. prosody and overlapping speech. It was decided t... | 16,841 | qmsum |
fdcdc0cf-ba1a-4483-8469-5d381305bf4b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What were the main discussion points of the meeting?\n\nProfessor E: So . OK . Doesn't look like it crashed . That 's great .\nGrad G: So I think maybe what 's causing it to crash is I keep starting it and then stopping it to see if i... | [
"The group discussed topics including a potential collaboration with another ICSI member regarding the analysis of inference structures, efforts by speaker mn005 to detect speaker overlap, the current status of recordings and transcriptions, and future efforts to collect meeting data. In addition to weekly meetings... | 26,113 | qmsum |
0b0ba672-2191-4c76-be0c-e53474d06d55 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they utilize unlabeled data to improve model representations?\n\nIntroduction\nAutomatic summarization, machine translation, question answering, and semantic parsing operations are useful for processing, analyzing, and extracti... | [
"During training, the model is trained alternately with one mini-batch of labeled data and INLINEFORM0 mini-batches of unlabeled data."
] | 9,318 | qasper |
1030ac8f-4c07-424d-a8dc-a79684577be8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the performance of classifiers?\n\nIntroduction\nA large portion of the car-buying experience in the United States involves interactions at a car dealership BIBREF0, BIBREF1, BIBREF2. Traditionally, a car dealer listens and un... | [
"Table TABREF10, The KNN classifier seem to perform the best across all four metrics. This is probably due to the multi-class nature of the data set, While these classifiers did not perform particularly well, they provide a good starting point for future work on this subject"
] | 2,203 | qasper |
244c3cf7-aa82-4e39-a454-8c2b505b8830 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"After how many hops does accuracy decrease?\n\nIntroduction\nAutomatically answering questions, especially in the open-domain setting (i.e., where minimal or no contextual knowledge is explicitly provided), requires bringing to bear c... | [
"one additional hop"
] | 9,200 | qasper |
3181f85f-c8cc-469a-881f-275a589cdb9a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they perform error analysis?\n\nIntroduction\nIn this digital era, online discussions and interactions has become a vital part of daily life of which a huge part is covered by social media platforms like twitter, facebook, instagra... | [
"No"
] | 3,366 | qasper |
31976677-2679-4d45-aee2-af062f374cc8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baselines did they consider?\n\nIntroduction\nExplanations of happenings in one's life, causal explanations, are an important topic of study in social, psychological, economic, and behavioral sciences. For example, psychologists ... | [
"Linear SVM, RBF SVM, and Random Forest"
] | 5,199 | qasper |
44042104-a9e6-4f69-95bb-b5a047669ab2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is evaluation performed?\n\nIntroduction\nNatural languages evolve and words have always been subject to semantic change over time BIBREF1. With the rise of large digitized text resources recent NLP technologies have made it possi... | [
"As the metric to assess how well the model's output fits the gold ranking Spearman's $\\rho $ was used"
] | 2,619 | qasper |
4b79812b-03d0-45d9-96b3-6290c627cf14 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the dataset balanced between speakers of different L1s?\n\nIntroduction\nSeveral learner corpora have been compiled for English, such as the International Corpus of Learner English BIBREF0 . The importance of such resources has bee... | [
"No"
] | 2,674 | qasper |
53778adc-1921-4d5c-8d61-dd8b7586157e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they use datasets with transcribed text or do they determine text from the audio?\n\nIntroduction\nRecently, deep learning algorithms have successfully addressed problems in various fields, such as image classification, machine tra... | [
"both"
] | 4,320 | qasper |
57d7452b-6d87-4536-a1cf-5d8d2889f9c9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which additional latent variables are used in the model?\n\nIntroduction\nSemantic Role Labeling (SRL) has emerged as an important task in Natural Language Processing (NLP) due to its applicability in information extraction, question ... | [
"crosslingual latent variables"
] | 5,272 | qasper |
76178aec-602c-4aa2-9dd6-55e66bfd000c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which languages are part of the corpus?\n\nIntroduction\nEnd-to-end speech-to-text translation (ST) has attracted much attention recently BIBREF2, BIBREF3, BIBREF4, BIBREF5, BIBREF6 given its simplicity against cascading automatic spe... | [
"French, German, Dutch, Russian, Spanish, Italian, Turkish, Persian, Swedish, Mongolian and Chinese"
] | 3,598 | qasper |
7e96093c-63e6-403a-b5ca-fd9f418973a2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the authors also try the model on other datasets?\n\nIntroduction\nSingle-relation factoid questions are the most common form of questions found in search query logs and community question answering websites BIBREF1 , BIBREF2 . A k... | [
"No"
] | 5,342 | qasper |
9f1f655c-0f24-448b-82e0-fca1e1d3131a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset is used in this paper?\n\nIntroduction\nSummarization of large texts is still an open problem in language processing. People nowadays have lesser time and patience to go through large pieces of text which make automatic s... | [
"AMR Bank, CNN-Dailymail"
] | 5,731 | qasper |
ac84c5a2-959b-423b-b69b-3fda583295c1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is this dataset publicly available for commercial use?\n\nIntroduction and Related Work\nWith the widespread adoption of electronic health records (EHRs), medical data are being generated and stored digitally in vast quantities BIBREF... | [
"Yes"
] | 2,184 | qasper |
b8105554-5bd1-4bc7-aa4c-d3d8d83eb96c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what dataset was used?\n\nIntroduction\nWhen people shop for books online in e-book stores such as, e.g., the Amazon Kindle store, they enter search terms with the goal to find e-books that meet their preferences. Such e-books have a ... | [
" E-book annotation data: editor tags, Amazon search terms, and Amazon review keywords."
] | 4,423 | qasper |
bf1985c7-19df-4a83-8ef9-0d2e5867c1c2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which additional latent variables are used in the model?\n\nIntroduction\nSemantic Role Labeling (SRL) has emerged as an important task in Natural Language Processing (NLP) due to its applicability in information extraction, question ... | [
"CLV as a parent of the two corresponding role variables"
] | 5,272 | qasper |
e5e0b666-447e-453f-af5f-1f5253b25d4d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many question types do they find in the datasets analyzed?\n\nIntroduction\nQuestion answering (QA) has been a blooming research field for the last decade. Selection-based QA implies a family of tasks that find answer contexts fro... | [
"7"
] | 2,607 | qasper |
efaeee3e-31e9-4e6a-b2ca-71b99766077c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they use active learning to create their dataset?\n\nIntroduction\nProgress in AI has been driven by, among other things, the development of challenging large-scale benchmarks like ImageNet BIBREF0 in computer vision, and SNLI BIBR... | [
"No"
] | 6,705 | qasper |
0d6bf9e7-014f-4beb-8e5c-688339abea27 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"On which benchmarks they achieve the state of the art?\n\nIntroduction\nKnowledge Base Question Answering (KBQA) systems answer questions by obtaining information from KB tuples BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , BIBREF4 , BIBREF... | [
"SimpleQuestions, WebQSP"
] | 6,739 | qasper |
1967e798-f237-48a2-8e82-484eb477e2f6 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What details are given about the movie domain dataset?\n\nIntroduction\nSentiment analysis has recently been one of the hottest topics in natural language processing (NLP). It is used to identify and categorise opinions expressed by r... | [
"there are 20,244 reviews divided into positive and negative with an average 39 words per review, each one having a star-rating score"
] | 5,006 | qasper |
22fde034-2bd2-45f6-ba86-26c7da96fcf9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Can named entities in SnapCaptions be discontigious?\n\nIntroduction\nSocial media with abundant user-generated posts provide a rich platform for understanding events, opinions and preferences of groups and individuals. These insights... | [
"No"
] | 5,444 | qasper |
26ff34b3-f1a5-4003-8630-d494a1b00f63 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which lstm models did they compare with?\n\nIntroduction\nRecently, deep neural network has been widely employed in various recognition tasks. Increasing the depth of neural network is a effective way to improve the performance, and c... | [
"Unidirectional LSTM networks with 2, 6, 7, 8, and 9 layers."
] | 5,552 | qasper |
291836ac-47a1-4aeb-9f35-11e054ee10ba | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are meaningful chains in the graph selected?\n\nIntroduction\nKnowledge graphs BIBREF0 enable structured access to world knowledge and form a key component of several applications like search engines, question answering systems an... | [
"utilize the machinery of language modeling using deep neural networks to learn Dolores embeddings."
] | 6,212 | qasper |
599ac615-2a0f-48ca-b9ca-4d15acfa9fd1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How did they obtain the dataset?\n\nIntroduction\nSocial media platforms have made the spreading of fake news easier, faster as well as able to reach a wider audience. Social media offer another feature which is the anonymity for the ... | [
"public resources where suspicious Twitter accounts were annotated, list with another 32 Twitter accounts from BIBREF19 that are considered trustworthy"
] | 2,882 | qasper |
5a507638-78b8-4d7c-bad5-8f39e68d00bb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What other tasks do they test their method on?\n\nIntroduction\nWe understand from Zipf's Law that in any natural language corpus a majority of the vocabulary word types will either be absent or occur in low frequency. Estimating the ... | [
"None"
] | 3,479 | qasper |
6d312416-e862-4f75-ab51-76fdcd86f83d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they use pretrained models?\n\nIntroduction\nDeep neural networks (DNNs), in particular convolutional and recurrent neural networks, with huge architectures have been proven successful in wide range of tasks including audio process... | [
"No"
] | 4,142 | qasper |
6fd8c1b0-4af8-473b-abd0-46c5d7f4eb8a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What type of neural model was used?\n\nIntroduction\nPrivacy policies are the documents which disclose the ways in which a company gathers, uses, shares and manages a user's data. As legal documents, they function using the principle ... | [
"Bert + Unanswerable"
] | 5,279 | qasper |
7b1ba3a3-c3c2-42be-99a5-ac151b247062 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Why are statistics from finite corpora unreliable?\n\nIntroduction\nDense word vectors (or embeddings) are a key component in modern NLP architectures for tasks such as sentiment analysis, parsing, and machine translation. These vecto... | [
"A finite corpora may entirely omit rare word combinations"
] | 3,414 | qasper |
7f1caf0d-1e88-44bc-86d6-80cfc296f70e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which sports clubs are the targets?\n\nIntroduction\nStance detection (also called stance identification or stance classification) is one of the considerably recent research topics in natural language processing (NLP). It is usually d... | [
"Galatasaray, Fenerbahçe"
] | 2,821 | qasper |
80c308c3-e515-4811-a6b6-3c35a93ab89b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what datasets were used?\n\nIntroduction\nEmotion detection has long been a topic of interest to scholars in natural language processing (NLP) domain. Researchers aim to recognize the emotion behind the text and distribute similar one... | [
"EmotionLines BIBREF6"
] | 4,509 | qasper |
9301d7d8-7bd9-4309-9eb5-addb533588de | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was the dataset annotated?\n\nIntroduction\nTask-oriented dialog systems have become ubiquitous, providing a means for billions of people to interact with computers using natural language. Moreover, the recent influx of platforms ... | [
"manually "
] | 3,154 | qasper |
a3f6f04e-9525-4a1c-a139-cc267cba3ae6 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What functionality does Macaw provide?\n\nIntroduction\nThe rapid growth in speech and small screen interfaces, particularly on mobile devices, has significantly influenced the way users interact with intelligent systems to satisfy th... | [
"conversational search, conversational question answering, conversational recommendation, conversational natural language interface to structured and semi-structured data"
] | 2,270 | qasper |
d1d15ac8-873d-4899-9ac6-6fa88035ce95 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the template-based model realistic? \n\nIntroduction\nRecently, with the emergence of neural seq2seq models, abstractive summarization methods have seen great performance strides BIBREF0, BIBREF1, BIBREF2. However, complex neural ... | [
"Yes"
] | 5,011 | qasper |
d62e93cc-3dee-43b1-a872-edde13959def | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the network's baseline features?\n\nIntroduction\nSarcasm is defined as “a sharp, bitter, or cutting expression or remark; a bitter gibe or taunt”. As the fields of affective computing and sentiment analysis have gained incre... | [
" The features extracted from CNN."
] | 6,600 | qasper |
f52aff45-4f82-4dae-b7a1-f5c011250bba | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the baselines used in the paper?\n\nIntroduction\nThe development of online peer-to-peer markets in the 1990s, galvanized by the launch of sites like eBay, fundamentally shifted the way buyers and sellers could connect [4]. T... | [
"Unanswerable"
] | 3,509 | qasper |
1edd2ed5-a9ba-4aa6-a8d7-f53bfe20e7d6 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline model is used?\n\nIntroduction\nSemantic Role Labeling (SRL) has emerged as an important task in Natural Language Processing (NLP) due to its applicability in information extraction, question answering, and other NLP tas... | [
"We use the same baseline as used by lang2011unsupervised which has been shown to be difficult to outperform. This baseline assigns a semantic role to a constituent based on its syntactic function, i.e. the dependency relation to its head."
] | 5,268 | qasper |
2083b99f-4a95-4a77-8301-61df513283ab | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what civil field is the dataset about?\n\nIntroduction\nAutomatic judgment prediction is to train a machine judge to determine whether a certain plea in a given civil case would be supported or rejected. In countries with civil law sy... | [
"divorce "
] | 5,476 | qasper |
3219badb-4c74-46bf-aa17-1ba823f19cee | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What other factors affect the performance?\n\nIntroduction\nAdversarial examples, a term introduced in BIBREF0, are inputs transformed by small perturbations that machine learning models consistently misclassify. The experiments are c... | [
"architecture of the classifier, sentence length, input domain"
] | 6,095 | qasper |
3ad0bcc5-08d5-42f0-b8c9-210338ac1b7d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the quality of singing voice measured?\n\nIntroduction\nSinging is an important way of human expression and the techniques of singing synthesis have broad applications in different prospects including virtual human, movie dubbi... | [
"Automatic: Normalized cross correlation (NCC)\nManual: Mean Opinion Score (MOS)"
] | 2,969 | qasper |
5cf3a64a-9c09-4b93-8c5c-ce8e274335c8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the strong baseline?\n\nIntroduction\nTable-to-text generation is an important and challenging task in natural language processing, which aims to produce the summarization of numerical table BIBREF0, BIBREF1. The related metho... | [
"Conditional Copy (CC) model "
] | 6,980 | qasper |
6245d21b-801f-422a-a5f4-bfee3214c767 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the size of the speech corpus?\n\nIntroduction\nTypical speech-to-text translation systems pipeline automatic speech recognition (ASR) and machine translation (MT) BIBREF0 . But high-quality ASR requires hundreds of hours of t... | [
"104 telephone calls, which pair 11 hours of audio"
] | 2,067 | qasper |
62b11bb8-7f37-4183-ba65-e3a2b75658e1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many annotators tagged each text?\n\nIntroduction\n“Laughter is the best Medicine” is a saying which is popular with most of the people. Humor is a form of communication that bridges the gap between various languages, cultures, ag... | [
"three "
] | 3,609 | qasper |
78634d3e-0d11-4b45-9ae9-00b6c0a879e4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline approaches does this approach out-perform?\n\nIntroduction\nWith the increasing popularity of the Internet, online texts provided by social media platform (e.g. Twitter) and news media sites (e.g. Google news) have becom... | [
"K-means, LEM BIBREF13, DPEMM BIBREF14"
] | 5,497 | qasper |
829fc2cf-8591-486d-9186-e8855bcb2352 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the authors train a Naive Bayes classifier on their dataset?\n\nIntroduction\nNamed Entity Recognition (NER) is a foremost NLP task to label each atomic elements of a sentence into specific categories like \"PERSON\", \"LOCATION\",... | [
"No"
] | 4,293 | qasper |
8cc1520a-17f5-4fc8-9347-ffb69678ca28 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they use other evaluation metrics besides ROUGE?\n\nIntroduction\nAutomatic summarization has enjoyed wide popularity in natural language processing due to its potential for various information access applications. Examples include... | [
"No"
] | 3,868 | qasper |
a46f73bc-880c-4510-99f8-2050a4703eef | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset did they use?\n\nIntroduction\nUnderstanding the emotions expressed in a text or message is of high relevance nowadays. Companies are interested in this to get an understanding of the sentiment of their current customers ... | [
" Selection of tweets with for each tweet a label describing the intensity of the emotion or sentiment provided by organizers and tweets translated form English to Spanish."
] | 3,098 | qasper |
b1a1afcd-3499-45a2-a53f-777730c23ae0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\n\nIntroduction\nWikipedia is the largest source of open and collaboratively curated knowledge in the world. Introduced in 2001, it has evolved into a reference work with around 5m pages fo... | [
"Yes"
] | 10,239 | qasper |
d0f840b7-b33e-41e9-afc0-0452bb06743a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big is dataset of car-speak language?\n\nIntroduction\nA large portion of the car-buying experience in the United States involves interactions at a car dealership BIBREF0, BIBREF1, BIBREF2. Traditionally, a car dealer listens and ... | [
"$3,209$ reviews "
] | 2,206 | qasper |
d9d7da5e-4656-49d4-83dc-362287077816 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baselines do they introduce?\n\nIntroduction\nThe automatic processing of medical texts and documents plays an increasingly important role in the recent development of the digital health area. To enable dedicated Natural Language... | [
"Conditional Random Fields, BiLSTM-CRF, Multi-Task Learning, BioBERT\n"
] | 3,588 | qasper |
dbc5bc77-a861-4741-9260-a5f55e5e7ec8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What classifiers have been trained?\n\nIntroduction\nA large portion of the car-buying experience in the United States involves interactions at a car dealership BIBREF0, BIBREF1, BIBREF2. Traditionally, a car dealer listens and unders... | [
" K Nearest Neighbors (KNN), Random Forest (RF), Support Vector Machine (SVM), Multi-layer Perceptron (MLP)"
] | 2,202 | qasper |
dce37462-2faa-4b36-8655-de6345bbcb51 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"When is this paper published?\n\nIntroduction\nText summarization generates summaries from input documents while keeping salient information. It is an important task and can be applied to several real-world applications. Many methods ... | [
"Unanswerable"
] | 5,685 | qasper |
e7dbfcfd-e5f1-4d64-a9ca-2b24b2100e7b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they measure which words are under-translated by NMT models?\n\nIntroduction\nNeural machine translation (NMT) has achieved the state-of-the-art results on a mass of language pairs with varying structural differences, such as E... | [
"we ask ten human annotators to manually label the under-translated input words, and at least two annotators label each input-hypothesis pair"
] | 5,825 | qasper |
ed9672e1-9259-4fe3-bb24-150c23a3e317 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What end tasks do they evaluate on?\n\nIntroduction\nDespite the rapid progress of deep learning techniques on diverse supervised learning tasks, these models remain brittle to subtle shifts in the data distribution. Even when the per... | [
"Sentiment analysis and paraphrase detection under adversarial attacks"
] | 5,902 | qasper |
f8679646-1504-4243-b3a6-e5e78aeacdfc | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which 7 Indian languages do they experiment with?\n\nINTRODUCTION\nThe idea of language identification is to classify a given audio signal into a particular class using a classification algorithm. Commonly language identification task... | [
"Kannada, Hindi, Telugu, Malayalam, Bengali, English and Assamese (in table, missing in text)"
] | 3,270 | qasper |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.