ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Hierarchical fusion of common sense knowledge and classifier decisions for answer selection in community question answering

Yang, Min; Chen, Lei; Lyu, Ziyu*; Liu, Junhao; Shen, Ying; Wu, Qingyao中山大学; 中国科学院
Neural Networks2020-12DOI: 10.1016/j.neunet.2020.08.005
13被引3阅读
引用收藏
分享

摘要

The goal of answer selection is to select the most applicable answers from an answer candidate pool. It plays an essential role in numerous applications in information retrieval (IR) and natural language processing (NLP). In this paper, we introduce a novel Knowledge-enhanced Hierarchical Attention mechanism for Answer Selection (KHAAS), which fully exploits the common sense knowledge from knowledge bases (KBs) and input textual information. Specifically, we first devise a three -stage knowledge-enhanced hierarchical attention mechanism, including the word-level attention, the phrase-level attention, and the document-level attention to learn the fact-aware intra-document features within questions and answers by fusing the knowledge from both the question/answer and KB. Hence, we can leverage the semantic compositionality of the question/answer and learn more holistic knowledge-enhanced intra-document features of the question/answer at three levels of granularity. Second, after obtaining the knowledge-enhanced question and answer representations, we employ a multi-perspective co-attention network to learn the complex inter-document relationships between the question and answer representations from different representation subspaces, which can capture the interactive semantics of the question and answer representations at three levels. Finally, we propose an adaptive decision fusion method to learn a more effective and robust ensemble answer selection model by adaptively combining multiple classifiers learned with different levels of features. Experimental results on three large-scale answer selection datasets demonstrate that KHAAS consistently outperforms the compared methods.

学科与关键词

关键词
Answer selectionCommon sense knowledgeHierarchical attentionSemantic compositionality
相关
加载中…
  • BertHANK: hierarchical attention networks with enhanced knowledge and pre-trained model for answer selection
    Yang, Haitian*; Zhao, Xuan; Wang, Yan*; Sun, Degang; Chen, Wei; Huang, WeiqingKNOWLEDGE AND INFORMATION SYSTEMS, 2022, 64(8): 2189-2213.
  • Knowledge-enhanced attentive learning for answer selection in community question answering systems
    Jing, Fengshi; Ren, Hao; Cheng, Weibin; Wang, Xin; Zhang, Qingpeng*Knowledge-Based Systems, 2022, 250: 109117.被引 3
  • DGQAN: Dual Graph Question-Answer Attention Networks for Answer Selection
    Yang, Haitian; Zhao, Xuan; Wang, Yan*; Li, Min; Chen, Wei; Huang, Weiqing45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), Madrid, SPAIN, 2022-07-11 To 2022-07-15.被引 1
查看全部 →

发表信息

论文状态
公开发表
期刊
Neural Networks
发表日期
2020-12
卷期
第 132 卷
页码
53-65
DOI
10.1016/j.neunet.2020.08.005
语言
ENGLISH
期刊收录
NSL.SCIE
期刊等级
2区
成果收录
SCIE
资助标注
National Natural Science Foundation of China [61906185]; Natural Science Foundation of Guangdong Province of China [2019A1515011705, 2018A030313943]; Shenzhen Basic Research Foundation [JCYJ20180302145645821, JCYJ20180302145633177]; SIAT Innovation Program for Excellent Young Researchers

作者

  • Y

    Yang, Min (第一作者)

    chinese acad sci

  • C

    Chen, Lei

    chinese acad sci

查看全部 6 位作者收起作者
  • L

    Lyu, Ziyu (通讯)

    chinese acad sci

  • L

    Liu, Junhao

    chinese acad sci

  • S

    Shen, Ying

    sun yat sen univ

  • W

    Wu, Qingyao

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417