Context modeling with evidence filter for multiple choice question answering
Multiple-Choice Question Answering (MCQA) is one of the challenging tasks in machine reading comprehension. The main challenge in MCQA is to extract "evidence" from the given context that supports the correct answer. In OpenbookQA dataset [1], the requirement of extracting "evidence&q...
Saved in:
Main Authors: | , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7615 https://ink.library.smu.edu.sg/context/sis_research/article/8618/viewcontent/2010.02649.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-8618 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-86182023-02-10T03:28:44Z Context modeling with evidence filter for multiple choice question answering YU, Sicheng ZHANG, Hao JING, Wei JIANG, Jing Multiple-Choice Question Answering (MCQA) is one of the challenging tasks in machine reading comprehension. The main challenge in MCQA is to extract "evidence" from the given context that supports the correct answer. In OpenbookQA dataset [1], the requirement of extracting "evidence" is particularly important due to the mutual independence of sentences in the context. Existing work tackles this problem by annotated evidence or distant supervision with rules which overly rely on human efforts. To address the challenge, we propose a simple yet effective approach termed evidence filtering to model the relationships between the encoded contexts with respect to different options collectively, and to potentially highlight the evidence sentences and filter out unrelated sentences. In addition to the effective reduction of human efforts of our approach compared, through extensive experiments on OpenbookQA, we show that the proposed approach outperforms the models that use the same backbone and more training data; and our parameter analysis also demonstrates the interpretability of our approach. 2022-05-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7615 info:doi/10.1109/ICASSP43922.2022.9747889 https://ink.library.smu.edu.sg/context/sis_research/article/8618/viewcontent/2010.02649.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Evidence Extraction Machine Reading Comprehension Natural Language Processing Question Answering Databases and Information Systems |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Evidence Extraction Machine Reading Comprehension Natural Language Processing Question Answering Databases and Information Systems |
spellingShingle |
Evidence Extraction Machine Reading Comprehension Natural Language Processing Question Answering Databases and Information Systems YU, Sicheng ZHANG, Hao JING, Wei JIANG, Jing Context modeling with evidence filter for multiple choice question answering |
description |
Multiple-Choice Question Answering (MCQA) is one of the challenging tasks in machine reading comprehension. The main challenge in MCQA is to extract "evidence" from the given context that supports the correct answer. In OpenbookQA dataset [1], the requirement of extracting "evidence" is particularly important due to the mutual independence of sentences in the context. Existing work tackles this problem by annotated evidence or distant supervision with rules which overly rely on human efforts. To address the challenge, we propose a simple yet effective approach termed evidence filtering to model the relationships between the encoded contexts with respect to different options collectively, and to potentially highlight the evidence sentences and filter out unrelated sentences. In addition to the effective reduction of human efforts of our approach compared, through extensive experiments on OpenbookQA, we show that the proposed approach outperforms the models that use the same backbone and more training data; and our parameter analysis also demonstrates the interpretability of our approach. |
format |
text |
author |
YU, Sicheng ZHANG, Hao JING, Wei JIANG, Jing |
author_facet |
YU, Sicheng ZHANG, Hao JING, Wei JIANG, Jing |
author_sort |
YU, Sicheng |
title |
Context modeling with evidence filter for multiple choice question answering |
title_short |
Context modeling with evidence filter for multiple choice question answering |
title_full |
Context modeling with evidence filter for multiple choice question answering |
title_fullStr |
Context modeling with evidence filter for multiple choice question answering |
title_full_unstemmed |
Context modeling with evidence filter for multiple choice question answering |
title_sort |
context modeling with evidence filter for multiple choice question answering |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2022 |
url |
https://ink.library.smu.edu.sg/sis_research/7615 https://ink.library.smu.edu.sg/context/sis_research/article/8618/viewcontent/2010.02649.pdf |
_version_ |
1770576394844110848 |