MGRC: An End-to-End Multigranularity Reading Comprehension Model for Question Answering.

Liu, Q; Geng, X; Huang, H; Qin, T; Lu, J; Jiang, D

MGRC: An End-to-End Multigranularity Reading Comprehension Model for Question Answering.

Liu, Q Geng, X Huang, H Qin, T Lu, J

Jiang, D

Permalink

Publisher:: Institute of Electrical and Electronics Engineers
Publication Type:: Journal Article
Citation:: IEEE Transactions on Neural Networks and Learning Systems, 2022, PP, (99)
Issue Date:: 2022-09-03

Closed Access

	Filename	Description	Size
	MGRC_An_End-to-End_Multigranularity_Reading_Comprehension_Model_for_Question_Answering.pdf	Published version	1.89 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Liu, Q
dc.contributor.author	Geng, X
dc.contributor.author	Huang, H
dc.contributor.author	Qin, T
dc.contributor.author	Lu, J https://orcid.org/0000-0003-0690-4732
dc.contributor.author	Jiang, D
dc.date.accessioned	2023-03-23T05:55:50Z
dc.date.available	2023-03-23T05:55:50Z
dc.date.issued	2022-09-03
dc.identifier.citation	IEEE Transactions on Neural Networks and Learning Systems, 2022, PP, (99)
dc.identifier.issn	1045-9227
dc.identifier.issn	2162-2388
dc.identifier.uri	http://hdl.handle.net/10453/168228
dc.description.abstract	Deep neural network-based models have achieved great success in extractive question answering. Recently, many works have been proposed to model multistage matching for this task, which usually first retrieve relevant paragraphs or sentences and then extract an answer span from the retrieved results. However, such a pipeline-based approach suffers from the error propagation problem, especially for sentence-level retrieval that is usually difficult to achieve high accuracy due to the severe data imbalance problem. Furthermore, since the paragraph/sentence selector and the answer extractor are closely related, modeling them independently does not fully exploit the power of multistage matching. To solve these problems, we propose a novel end-to-end multigranularity reading comprehension model, which is a unified framework to explicitly model three matching granularities, including paragraph identification, sentence selection, and answer extraction. Our approach has two main advantages. First, the end-to-end approach alleviates the error propagation problem in both the training and inference phases. Second, the shared features in a unified model improve the learning of representations of different matching granularities. We conduct a comprehensive comparison on four large-scale datasets (SQuAD-open, NewsQA, SQuAD 2.0, and SQuAD Adversarial) and verify that the proposed approach outperforms both the vanilla BERT model and existing multistage matching approaches. We also conduct an ablation study and verify the effectiveness of the proposed components in our model structure.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	Institute of Electrical and Electronics Engineers
dc.relation.ispartof	IEEE Transactions on Neural Networks and Learning Systems
dc.relation.isbasedon	10.1109/TNNLS.2021.3107029
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	MGRC: An End-to-End Multigranularity Reading Comprehension Model for Question Answering.
dc.type	Journal Article
utslib.citation.volume	PP
utslib.location.activity	United States
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2023-03-23T05:55:48Z
pubs.issue	99
pubs.publication-status	Published online
pubs.volume	PP
utslib.citation.issue	99

Abstract:

Deep neural network-based models have achieved great success in extractive question answering. Recently, many works have been proposed to model multistage matching for this task, which usually first retrieve relevant paragraphs or sentences and then extract an answer span from the retrieved results. However, such a pipeline-based approach suffers from the error propagation problem, especially for sentence-level retrieval that is usually difficult to achieve high accuracy due to the severe data imbalance problem. Furthermore, since the paragraph/sentence selector and the answer extractor are closely related, modeling them independently does not fully exploit the power of multistage matching. To solve these problems, we propose a novel end-to-end multigranularity reading comprehension model, which is a unified framework to explicitly model three matching granularities, including paragraph identification, sentence selection, and answer extraction. Our approach has two main advantages. First, the end-to-end approach alleviates the error propagation problem in both the training and inference phases. Second, the shared features in a unified model improve the learning of representations of different matching granularities. We conduct a comprehensive comparison on four large-scale datasets (SQuAD-open, NewsQA, SQuAD 2.0, and SQuAD Adversarial) and verify that the proposed approach outperforms both the vanilla BERT model and existing multistage matching approaches. We also conduct an ablation study and verify the effectiveness of the proposed components in our model structure.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/168228