Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base

Shen, T; Geng, X; Qin, T; Guo, D; Tang, D; Duan, N; Long, G; Jiang, D

Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base

Shen, T Geng, X Qin, T Guo, D Tang, D Duan, N Long, G

Jiang, D

Permalink

Publication Type:: Journal Article
Citation:: 2019
Issue Date:: 2019-10-11

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (748.42 kB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Shen, T
dc.contributor.author	Geng, X
dc.contributor.author	Qin, T
dc.contributor.author	Guo, D
dc.contributor.author	Tang, D
dc.contributor.author	Duan, N
dc.contributor.author	Long, G https://orcid.org/0000-0003-3740-9515
dc.contributor.author	Jiang, D
dc.date.accessioned	2021-05-11T01:11:32Z
dc.date.available	2021-05-11T01:11:32Z
dc.date.issued	2019-10-11
dc.identifier.citation	2019
dc.identifier.uri	http://hdl.handle.net/10453/148828
dc.description.abstract	We consider the problem of conversational question answering over a large-scale knowledge base. To handle huge entity vocabulary of a large-scale knowledge base, recent neural semantic parsing based approaches usually decompose the task into several subtasks and then solve them sequentially, which leads to following issues: 1) errors in earlier subtasks will be propagated and negatively affect downstream ones; and 2) each subtask cannot naturally share supervision signals with others. To tackle these issues, we propose an innovative multi-task learning framework where a pointer-equipped semantic parsing model is designed to resolve coreference in conversations, and naturally empower joint learning with a novel type-aware entity detection model. The proposed framework thus enables shared supervisions and alleviates the effect of error propagation. Experiments on a large-scale conversational question answering dataset containing 1.6M question answering pairs over 12.8M entities show that the proposed framework improves overall F1 score from 67% to 79% compared with previous state-of-the-art work.
dc.language	en
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base
dc.type	Journal Article
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	open_access	*
dc.date.updated	2021-05-11T01:11:31Z

Abstract:

We consider the problem of conversational question answering over a large-scale knowledge base. To handle huge entity vocabulary of a large-scale knowledge base, recent neural semantic parsing based approaches usually decompose the task into several subtasks and then solve them sequentially, which leads to following issues: 1) errors in earlier subtasks will be propagated and negatively affect downstream ones; and 2) each subtask cannot naturally share supervision signals with others. To tackle these issues, we propose an innovative multi-task learning framework where a pointer-equipped semantic parsing model is designed to resolve coreference in conversations, and naturally empower joint learning with a novel type-aware entity detection model. The proposed framework thus enables shared supervisions and alleviates the effect of error propagation. Experiments on a large-scale conversational question answering dataset containing 1.6M question answering pairs over 12.8M entities show that the proposed framework improves overall F1 score from 67% to 79% compared with previous state-of-the-art work.

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

http://hdl.handle.net/10453/148828