Query graph generation for answering multi-hop complex questions from knowledge bases

Previous work on answering complex questions from knowledge bases usually separately addresses two types of complexity: questions with constraints and questions with multiple hops of relations. In this paper, we handle both types of complexity at the same time. Motivated by the observation that earl...

Full description

Saved in:
Bibliographic Details
Main Authors: LAN, Yunshi, Jing JIANG
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2020
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/5271
https://ink.library.smu.edu.sg/context/sis_research/article/6274/viewcontent/7._Query_Graph_Generation_for_Answering_Multi_hop_Complex_Questions__ACL2020_.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-6274
record_format dspace
spelling sg-smu-ink.sis_research-62742020-08-14T04:01:12Z Query graph generation for answering multi-hop complex questions from knowledge bases LAN, Yunshi Jing JIANG, Previous work on answering complex questions from knowledge bases usually separately addresses two types of complexity: questions with constraints and questions with multiple hops of relations. In this paper, we handle both types of complexity at the same time. Motivated by the observation that early incorporation of constraints into query graphs can more effectively prune the search space, we propose a modified staged query graph generation method with more flexible ways to generate query graphs. Our experiments clearly show that our method achieves the state of the art on three benchmark KBQA datasets. 2020-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/5271 info:doi/10.18653/v1/2020.acl-main.91 https://ink.library.smu.edu.sg/context/sis_research/article/6274/viewcontent/7._Query_Graph_Generation_for_Answering_Multi_hop_Complex_Questions__ACL2020_.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 Artificial Intelligence and Robotics Theory and Algorithms
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Artificial Intelligence and Robotics
Theory and Algorithms
spellingShingle Artificial Intelligence and Robotics
Theory and Algorithms
LAN, Yunshi
Jing JIANG,
Query graph generation for answering multi-hop complex questions from knowledge bases
description Previous work on answering complex questions from knowledge bases usually separately addresses two types of complexity: questions with constraints and questions with multiple hops of relations. In this paper, we handle both types of complexity at the same time. Motivated by the observation that early incorporation of constraints into query graphs can more effectively prune the search space, we propose a modified staged query graph generation method with more flexible ways to generate query graphs. Our experiments clearly show that our method achieves the state of the art on three benchmark KBQA datasets.
format text
author LAN, Yunshi
Jing JIANG,
author_facet LAN, Yunshi
Jing JIANG,
author_sort LAN, Yunshi
title Query graph generation for answering multi-hop complex questions from knowledge bases
title_short Query graph generation for answering multi-hop complex questions from knowledge bases
title_full Query graph generation for answering multi-hop complex questions from knowledge bases
title_fullStr Query graph generation for answering multi-hop complex questions from knowledge bases
title_full_unstemmed Query graph generation for answering multi-hop complex questions from knowledge bases
title_sort query graph generation for answering multi-hop complex questions from knowledge bases
publisher Institutional Knowledge at Singapore Management University
publishDate 2020
url https://ink.library.smu.edu.sg/sis_research/5271
https://ink.library.smu.edu.sg/context/sis_research/article/6274/viewcontent/7._Query_Graph_Generation_for_Answering_Multi_hop_Complex_Questions__ACL2020_.pdf
_version_ 1770575366232997888