Document-enhanced Question Answering over Knowledge-Bases
Recently,knowledge base(KB) has been widely adopted to the task of question answering(QA) to provide a proper answer for a given question,known as the KBQA problem.However,knowledge base itself may be incomplete(e.g.KB does not contain the answer to the question,or some of the entities and relations...
Main Author: | |
---|---|
Format: | Article |
Language: | zho |
Published: |
Editorial office of Computer Science
2023-03-01
|
Series: | Jisuanji kexue |
Subjects: | |
Online Access: | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2023-50-3-266.pdf |
_version_ | 1797845101693632512 |
---|---|
author | FENG Chengcheng, LIU Pai, JIANG Linying, MEI Xiaohan, GUO Guibing |
author_facet | FENG Chengcheng, LIU Pai, JIANG Linying, MEI Xiaohan, GUO Guibing |
author_sort | FENG Chengcheng, LIU Pai, JIANG Linying, MEI Xiaohan, GUO Guibing |
collection | DOAJ |
description | Recently,knowledge base(KB) has been widely adopted to the task of question answering(QA) to provide a proper answer for a given question,known as the KBQA problem.However,knowledge base itself may be incomplete(e.g.KB does not contain the answer to the question,or some of the entities and relationships in the question),limiting the overall performance of existing KBQA models.To resolve this issue,this paper proposes a new model to leverage textual documents for KBQA task by providing additional answers to enhance knowledge base coverage and background information to enhance the representation of questions.Specifically,the proposed model consists of three modules,namely entity and question representation module,document and enhanced-question representation module and answer prediction module.The first module aims to learn the representations of entities from the retrieved subgraph of knowledge base.Then,the question representation can be updated with the fusion of seed entities.The second module attempts to learn a proper representation of the document that is relevant to the given question.Then,the question representation can be further improved by fusing the document information.Finally,the last module makes an answer prediction based on the information of knowledge base,updated question and documents.Extensive experiments are conducted on the WebQuestionsSP dataset,and the results show that better accuracy can be obtained in comparison with other counterparts. |
first_indexed | 2024-04-09T17:33:06Z |
format | Article |
id | doaj.art-f68c20b0f30c4c82ae81b9c079abb559 |
institution | Directory Open Access Journal |
issn | 1002-137X |
language | zho |
last_indexed | 2024-04-09T17:33:06Z |
publishDate | 2023-03-01 |
publisher | Editorial office of Computer Science |
record_format | Article |
series | Jisuanji kexue |
spelling | doaj.art-f68c20b0f30c4c82ae81b9c079abb5592023-04-18T02:33:25ZzhoEditorial office of Computer ScienceJisuanji kexue1002-137X2023-03-0150326627510.11896/jsjkx.220300022Document-enhanced Question Answering over Knowledge-BasesFENG Chengcheng, LIU Pai, JIANG Linying, MEI Xiaohan, GUO Guibing01 School of Software,Northeastern University,Shenyang 110000,China;2 School of Engineering,Westlake University,Hangzhou 310000,China;3 School of Software,University of Maryland,Maryland MD20740,USARecently,knowledge base(KB) has been widely adopted to the task of question answering(QA) to provide a proper answer for a given question,known as the KBQA problem.However,knowledge base itself may be incomplete(e.g.KB does not contain the answer to the question,or some of the entities and relationships in the question),limiting the overall performance of existing KBQA models.To resolve this issue,this paper proposes a new model to leverage textual documents for KBQA task by providing additional answers to enhance knowledge base coverage and background information to enhance the representation of questions.Specifically,the proposed model consists of three modules,namely entity and question representation module,document and enhanced-question representation module and answer prediction module.The first module aims to learn the representations of entities from the retrieved subgraph of knowledge base.Then,the question representation can be updated with the fusion of seed entities.The second module attempts to learn a proper representation of the document that is relevant to the given question.Then,the question representation can be further improved by fusing the document information.Finally,the last module makes an answer prediction based on the information of knowledge base,updated question and documents.Extensive experiments are conducted on the WebQuestionsSP dataset,and the results show that better accuracy can be obtained in comparison with other counterparts.https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2023-50-3-266.pdfkb-qa|co-attention|end-to-end|neural network|fusion gate function |
spellingShingle | FENG Chengcheng, LIU Pai, JIANG Linying, MEI Xiaohan, GUO Guibing Document-enhanced Question Answering over Knowledge-Bases Jisuanji kexue kb-qa|co-attention|end-to-end|neural network|fusion gate function |
title | Document-enhanced Question Answering over Knowledge-Bases |
title_full | Document-enhanced Question Answering over Knowledge-Bases |
title_fullStr | Document-enhanced Question Answering over Knowledge-Bases |
title_full_unstemmed | Document-enhanced Question Answering over Knowledge-Bases |
title_short | Document-enhanced Question Answering over Knowledge-Bases |
title_sort | document enhanced question answering over knowledge bases |
topic | kb-qa|co-attention|end-to-end|neural network|fusion gate function |
url | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2023-50-3-266.pdf |
work_keys_str_mv | AT fengchengchengliupaijianglinyingmeixiaohanguoguibing documentenhancedquestionansweringoverknowledgebases |