Improving multi-hop knowledge base question answering by learning intermediate supervision signals

Multi-hop Knowledge Base Question Answering (KBQA) aims to find the answer entities that are multiple hops away in the Knowledge Base (KB) from the entities in the question. A major challenge is the lack of supervision signals at intermediate steps. Therefore, multi-hop KBQA algorithms can only rece...

Full description

Saved in:
Bibliographic Details
Main Authors: HE, Gaole, LAN, Yunshi, JIANG, Jing, ZHAO, Wayne Xin, WEN, Ji Rong
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2021
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/5892
https://ink.library.smu.edu.sg/context/sis_research/article/6895/viewcontent/2_Improving_Multi_hop_Knowledge_Base_WSDM2021_av.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-6895
record_format dspace
spelling sg-smu-ink.sis_research-68952021-04-16T01:08:13Z Improving multi-hop knowledge base question answering by learning intermediate supervision signals HE, Gaole LAN, Yunshi JIANG, Jing ZHAO, Wayne Xin WEN, Ji Rong Multi-hop Knowledge Base Question Answering (KBQA) aims to find the answer entities that are multiple hops away in the Knowledge Base (KB) from the entities in the question. A major challenge is the lack of supervision signals at intermediate steps. Therefore, multi-hop KBQA algorithms can only receive the feedback from the final answer, which makes the learning unstable or ineffective. To address this challenge, we propose a novel teacher-student approach for the multi-hop KBQA task. In our approach, the student network aims to find the correct answer to the query, while the teacher network tries to learn intermediate supervision signals for improving the reasoning capacity of the student network. The major novelty lies in the design of the teacher network, where we utilize both forward and backward reasoning to enhance the learning of intermediate entity distributions. By considering bidirectional reasoning, the teacher network can produce more reliable intermediate supervision signals, which can alleviate the issue of spurious reasoning. Extensive experiments on three benchmark datasets have demonstrated the effectiveness of our approach on the KBQA task. 2021-03-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/5892 info:doi/10.1145/3437963.3441753 https://ink.library.smu.edu.sg/context/sis_research/article/6895/viewcontent/2_Improving_Multi_hop_Knowledge_Base_WSDM2021_av.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 intermediate supervision signals knowledge base question answering teacher-student network Databases and Information Systems 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 intermediate supervision signals
knowledge base question answering
teacher-student network
Databases and Information Systems
Theory and Algorithms
spellingShingle intermediate supervision signals
knowledge base question answering
teacher-student network
Databases and Information Systems
Theory and Algorithms
HE, Gaole
LAN, Yunshi
JIANG, Jing
ZHAO, Wayne Xin
WEN, Ji Rong
Improving multi-hop knowledge base question answering by learning intermediate supervision signals
description Multi-hop Knowledge Base Question Answering (KBQA) aims to find the answer entities that are multiple hops away in the Knowledge Base (KB) from the entities in the question. A major challenge is the lack of supervision signals at intermediate steps. Therefore, multi-hop KBQA algorithms can only receive the feedback from the final answer, which makes the learning unstable or ineffective. To address this challenge, we propose a novel teacher-student approach for the multi-hop KBQA task. In our approach, the student network aims to find the correct answer to the query, while the teacher network tries to learn intermediate supervision signals for improving the reasoning capacity of the student network. The major novelty lies in the design of the teacher network, where we utilize both forward and backward reasoning to enhance the learning of intermediate entity distributions. By considering bidirectional reasoning, the teacher network can produce more reliable intermediate supervision signals, which can alleviate the issue of spurious reasoning. Extensive experiments on three benchmark datasets have demonstrated the effectiveness of our approach on the KBQA task.
format text
author HE, Gaole
LAN, Yunshi
JIANG, Jing
ZHAO, Wayne Xin
WEN, Ji Rong
author_facet HE, Gaole
LAN, Yunshi
JIANG, Jing
ZHAO, Wayne Xin
WEN, Ji Rong
author_sort HE, Gaole
title Improving multi-hop knowledge base question answering by learning intermediate supervision signals
title_short Improving multi-hop knowledge base question answering by learning intermediate supervision signals
title_full Improving multi-hop knowledge base question answering by learning intermediate supervision signals
title_fullStr Improving multi-hop knowledge base question answering by learning intermediate supervision signals
title_full_unstemmed Improving multi-hop knowledge base question answering by learning intermediate supervision signals
title_sort improving multi-hop knowledge base question answering by learning intermediate supervision signals
publisher Institutional Knowledge at Singapore Management University
publishDate 2021
url https://ink.library.smu.edu.sg/sis_research/5892
https://ink.library.smu.edu.sg/context/sis_research/article/6895/viewcontent/2_Improving_Multi_hop_Knowledge_Base_WSDM2021_av.pdf
_version_ 1770575643791065088