Multi-Hop Reasoning for Question Answering with Knowledge Graph

被引：1

作者：

Zhang, Jiayuan ^{[1
,2
]}

Cai, Yifei ^{[1
,2
]}

Zhang, Qian ^{[1
,2
]}

Cao, Zehao ^{[1
,2
]}

Cheng, Zhenrong ^{[1
,2
]}

Li, Dongmei ^{[1
,2
]}

Meng, Xianghao ^{[1
,2
]}

机构：

[1] Beijing Forestry Univ, Sch Informat Sci & Technol, Beijing, Peoples R China

[2] Natl Forestry & Grassland Adm, Engn Res Ctr Forestry Oriented Intelligent Inform, Beijing, Peoples R China

来源：

2021 IEEE/ACIS 20TH INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION SCIENCE (ICIS 2021-SUMMER) | 2021年

关键词：

Knowledge Graph; Question Answering System; CNN;

D O I：

10.1109/ICIS51600.2021.9516865

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Multi-hop Question Answering over Knowledge Graphs (KGQA) in previous studies has achieved remarkable results by exploiting the prediction property of Knowledge Graphs (KG) embedding. However, when facing Chinese sentences, its answer selection performs poorly. We improve the method for KGQA by combining the traditional method for KGQA with a lattice based CNN (LCN) model. We refine the granularity of questions and answers to make its coverage more extensive and generalizable, and expand the answer set to improve the performance in single results.

引用

页码：121 / 125

页数：5

共 50 条

[41] CogKR: Cognitive Graph for Multi-Hop Knowledge Reasoning
Du, Zhengxiao
Zhou, Chang
Yao, Jiangchao
Tu, Teng
Cheng, Letian
Yang, Hongxia
Zhou, Jingren
Tang, Jie
[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (02) : 1283 - 1295
[42] Incorporating anticipation embedding into reinforcement learning framework for multi-hop knowledge graph question answering
Cui, Hai
Peng, Tao
Xiao, Feng
Han, Jiayu
Han, Ridong
Liu, Lu
[J]. INFORMATION SCIENCES, 2023, 619 : 745 - 761
[43] GaussianPath:A Bayesian Multi-Hop Reasoning Framework for Knowledge Graph Reasoning
Wan, Guojia
Du, Bo
[J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 4393 - 4401
[44] Incorporating multi-perspective information into reinforcement learning to address multi-hop knowledge graph question answering
Gong, Chuanyang
Wei, Zhihua
Wang, Rui
Zhu, Ping
Chen, Jing
Zhang, Hongyun
Miao, Duoqian
[J]. EXPERT SYSTEMS WITH APPLICATIONS, 2024, 255
[45] Unsupervised Multi-hop Question Answering by Question Generation
Pan, Liangming
Chen, Wenhu
Xiong, Wenhan
Kan, Min-Yen
Wang, William Yang
[J]. 2021 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL-HLT 2021), 2021, : 5866 - 5880
[46] VIMQA: A Vietnamese Dataset for Advanced Reasoning and Explainable Multi-hop Question Answering
Le, Nguyen-Khang
Nguyen, Dieu-Hien
Le, Tung
Nguyen, Minh Le
[J]. LREC 2022: THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2022, : 6521 - 6529
[47] To hop or not, that is the question: Towards effective multi-hop reasoning over knowledge graphs
Jinzhi Liao
Xiang Zhao
Jiuyang Tang
Weixin Zeng
Zhen Tan
[J]. World Wide Web, 2021, 24 : 1837 - 1856
[48] Translational relation embeddings for multi-hop knowledge base question answering
Li, Ziyan
Wang, Haofen
Zhang, Wenqiang
[J]. JOURNAL OF WEB SEMANTICS, 2022, 74
[49] ExKGR: Explainable Multi-hop Reasoning for Evolving Knowledge Graph
Yan, Cheng
Zhao, Feng
Jin, Hai
[J]. DATABASE SYSTEMS FOR ADVANCED APPLICATIONS, DASFAA 2022, PT I, 2022, : 153 - 161
[50] BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering
Cao, Yu
Fang, Meng
Tao, Dacheng
[J]. 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, 2019, : 357 - 362

← 1 2 3 4 5 →