Dual-Channel Reasoning Model for Complex Question Answering
Multihop question answering has attracted extensive studies in recent years because of the emergence of human annotated datasets and associated leaderboards. Recent studies have revealed that question answering systems learn to exploit annotation artifacts and other biases in current datasets. There...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-01-01
|
Series: | Complexity |
Online Access: | http://dx.doi.org/10.1155/2021/7367181 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1832561515511676928 |
---|---|
author | Xing Cao Yun Liu Bo Hu Yu Zhang |
author_facet | Xing Cao Yun Liu Bo Hu Yu Zhang |
author_sort | Xing Cao |
collection | DOAJ |
description | Multihop question answering has attracted extensive studies in recent years because of the emergence of human annotated datasets and associated leaderboards. Recent studies have revealed that question answering systems learn to exploit annotation artifacts and other biases in current datasets. Therefore, a model with strong interpretability should not only predict the final answer, but more importantly find the supporting facts’ sentences necessary to answer complex questions, also known as evidence sentences. Most existing methods predict the final answer and evidence sentences in sequence or simultaneously, which inhibits the ability of models to predict the path of reasoning. In this paper, we propose a dual-channel reasoning architecture, where two reasoning channels predict the final answer and supporting facts’ sentences, respectively, while sharing the contextual embedding layer. The two reasoning channels can simply use the same reasoning structure without additional network designs. Through experimental analysis based on public question answering datasets, we demonstrate the effectiveness of our proposed method |
format | Article |
id | doaj-art-a205a9d803c1493a8614b1005f4972ff |
institution | Kabale University |
issn | 1076-2787 1099-0526 |
language | English |
publishDate | 2021-01-01 |
publisher | Wiley |
record_format | Article |
series | Complexity |
spelling | doaj-art-a205a9d803c1493a8614b1005f4972ff2025-02-03T01:24:48ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/73671817367181Dual-Channel Reasoning Model for Complex Question AnsweringXing Cao0Yun Liu1Bo Hu2Yu Zhang3School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, ChinaMultihop question answering has attracted extensive studies in recent years because of the emergence of human annotated datasets and associated leaderboards. Recent studies have revealed that question answering systems learn to exploit annotation artifacts and other biases in current datasets. Therefore, a model with strong interpretability should not only predict the final answer, but more importantly find the supporting facts’ sentences necessary to answer complex questions, also known as evidence sentences. Most existing methods predict the final answer and evidence sentences in sequence or simultaneously, which inhibits the ability of models to predict the path of reasoning. In this paper, we propose a dual-channel reasoning architecture, where two reasoning channels predict the final answer and supporting facts’ sentences, respectively, while sharing the contextual embedding layer. The two reasoning channels can simply use the same reasoning structure without additional network designs. Through experimental analysis based on public question answering datasets, we demonstrate the effectiveness of our proposed methodhttp://dx.doi.org/10.1155/2021/7367181 |
spellingShingle | Xing Cao Yun Liu Bo Hu Yu Zhang Dual-Channel Reasoning Model for Complex Question Answering Complexity |
title | Dual-Channel Reasoning Model for Complex Question Answering |
title_full | Dual-Channel Reasoning Model for Complex Question Answering |
title_fullStr | Dual-Channel Reasoning Model for Complex Question Answering |
title_full_unstemmed | Dual-Channel Reasoning Model for Complex Question Answering |
title_short | Dual-Channel Reasoning Model for Complex Question Answering |
title_sort | dual channel reasoning model for complex question answering |
url | http://dx.doi.org/10.1155/2021/7367181 |
work_keys_str_mv | AT xingcao dualchannelreasoningmodelforcomplexquestionanswering AT yunliu dualchannelreasoningmodelforcomplexquestionanswering AT bohu dualchannelreasoningmodelforcomplexquestionanswering AT yuzhang dualchannelreasoningmodelforcomplexquestionanswering |