Bridging Information-Seeking Human Gaze and Machine Reading Comprehension
In this work, we analyze how human gaze during reading comprehension is conditioned on the given reading comprehension question, and whether this signal can be beneficial for machine reading comprehension. To this end, we collect a new eye-tracking dataset with a large number of participants e...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Association for Computational Linguistics (ACL)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/138276 |
| _version_ | 1811088651914838016 |
|---|---|
| author | Malmaud, Jonathan Levy, Roger Berzak, Yevgeni |
| author2 | Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences |
| author_facet | Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences Malmaud, Jonathan Levy, Roger Berzak, Yevgeni |
| author_sort | Malmaud, Jonathan |
| collection | MIT |
| description | In this work, we analyze how human gaze
during reading comprehension is conditioned
on the given reading comprehension question,
and whether this signal can be beneficial for
machine reading comprehension. To this end,
we collect a new eye-tracking dataset with a
large number of participants engaging in a multiple choice reading comprehension task. Our
analysis of this data reveals increased fixation
times over parts of the text that are most relevant for answering the question. Motivated
by this finding, we propose making automated
reading comprehension more human-like by
mimicking human information-seeking reading behavior during reading comprehension.
We demonstrate that this approach leads to performance gains on multiple choice question answering in English for a state-of-the-art reading comprehension model. |
| first_indexed | 2024-09-23T14:05:22Z |
| format | Article |
| id | mit-1721.1/138276 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T14:05:22Z |
| publishDate | 2021 |
| publisher | Association for Computational Linguistics (ACL) |
| record_format | dspace |
| spelling | mit-1721.1/1382762023-02-13T18:26:08Z Bridging Information-Seeking Human Gaze and Machine Reading Comprehension Malmaud, Jonathan Levy, Roger Berzak, Yevgeni Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences In this work, we analyze how human gaze during reading comprehension is conditioned on the given reading comprehension question, and whether this signal can be beneficial for machine reading comprehension. To this end, we collect a new eye-tracking dataset with a large number of participants engaging in a multiple choice reading comprehension task. Our analysis of this data reveals increased fixation times over parts of the text that are most relevant for answering the question. Motivated by this finding, we propose making automated reading comprehension more human-like by mimicking human information-seeking reading behavior during reading comprehension. We demonstrate that this approach leads to performance gains on multiple choice question answering in English for a state-of-the-art reading comprehension model. 2021-12-01T17:28:44Z 2021-12-01T17:28:44Z 2020 2021-12-01T17:26:29Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/138276 Malmaud, Jonathan, Levy, Roger and Berzak, Yevgeni. 2020. "Bridging Information-Seeking Human Gaze and Machine Reading Comprehension." Proceedings of the 24th Conference on Computational Natural Language Learning. en 10.18653/V1/2020.CONLL-1.11 Proceedings of the 24th Conference on Computational Natural Language Learning Creative Commons Attribution 4.0 International license https://creativecommons.org/licenses/by/4.0/ application/pdf Association for Computational Linguistics (ACL) Association for Computational Linguistics |
| spellingShingle | Malmaud, Jonathan Levy, Roger Berzak, Yevgeni Bridging Information-Seeking Human Gaze and Machine Reading Comprehension |
| title | Bridging Information-Seeking Human Gaze and Machine Reading Comprehension |
| title_full | Bridging Information-Seeking Human Gaze and Machine Reading Comprehension |
| title_fullStr | Bridging Information-Seeking Human Gaze and Machine Reading Comprehension |
| title_full_unstemmed | Bridging Information-Seeking Human Gaze and Machine Reading Comprehension |
| title_short | Bridging Information-Seeking Human Gaze and Machine Reading Comprehension |
| title_sort | bridging information seeking human gaze and machine reading comprehension |
| url | https://hdl.handle.net/1721.1/138276 |
| work_keys_str_mv | AT malmaudjonathan bridginginformationseekinghumangazeandmachinereadingcomprehension AT levyroger bridginginformationseekinghumangazeandmachinereadingcomprehension AT berzakyevgeni bridginginformationseekinghumangazeandmachinereadingcomprehension |