Learning the Extraction Order of Multiple Relational Facts in a Sentence with Reinforcement Learning

被引：0
|
作者：
Zeng, Xiangrong [1 ,2 ,3 ]
He, Shizhu [1 ,2 ]
Zeng, Daojian [4 ]
Liu, Kang [1 ,2 ]
Zhao, Jun [1 ,2 ]
机构：
[1] Chinese Acad Sci, Inst Automat, NLPR, Beijing 100190, Peoples R China
[2] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
[3] Unisound AI Technol Co Ltd, Beijing 100000, Peoples R China
[4] Changsha Univ Sci & Technol, Changsha 410114, Peoples R China
来源：
2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE | 2019年
基金：
中国国家自然科学基金;
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The multiple relation extraction task tries to extract all relational facts from a sentence. Existing works didn't consider the extraction order of relational facts in a sentence. In this paper we argue that the extraction order is important in this task. To take the extraction order into consideration, we apply the reinforcement learning into a sequence-to-sequence model. The proposed model could generate relational facts freely. Widely conducted experiments on two public datasets demonstrate the efficacy of the proposed method.
引用
收藏
页码：367 / 377
页数：11
相关论文
共 50 条
  • [1] Semantic Extraction for Sentence Representation via Reinforcement Learning
    Yu, Fengying
    Tao, Dewei
    Wang, Jianzong
    Hui, Yanfei
    Cheng, Ning
    Xiao, Jing
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [2] Relational reinforcement learning
    Driessens, K
    AI COMMUNICATIONS, 2005, 18 (01) : 71 - 73
  • [3] Relational reinforcement learning
    Driessens, K
    MULTI-AGENT SYSTEMS AND APPLICATIONS, 2001, 2086 : 271 - 280
  • [4] Relational reinforcement learning
    Dzeroski, S
    De Raedt, L
    Driessens, K
    MACHINE LEARNING, 2001, 43 (1-2) : 7 - 52
  • [5] Relational Reinforcement Learning
    Sašo Džeroski
    Luc De Raedt
    Kurt Driessens
    Machine Learning, 2001, 43 : 7 - 52
  • [6] Sentence Compression with Reinforcement Learning
    Wang, Liangguo
    Jiang, Jing
    Liao, Lejian
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT (KSEM 2018), PT I, 2018, 11061 : 3 - 15
  • [7] Learning relational options for inductive transfer in relational reinforcement learning
    Croonenborghs, Tom
    Driessens, Kurt
    Bruynooghe, Maurice
    INDUCTIVE LOGIC PROGRAMMING, 2008, 4894 : 88 - 97
  • [8] An Enhancement of Relational Reinforcement Learning
    da Silva, Renato R.
    Policastro, Claudio A.
    Romero, Roseli A. F.
    2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8, 2008, : 2055 - 2060
  • [9] Online Learning and Exploiting Relational Models in Reinforcement Learning
    Croonenborghs, Tom
    Ramon, Jan
    Blockeel, Hendrik
    Bruynooghe, Maurice
    20TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2007, : 726 - 731
  • [10] Reinforcement Learning With Multiple Relational Attention for Solving Vehicle Routing Problems
    Xu, Yunqiu
    Fang, Meng
    Chen, Ling
    Xu, Gangyan
    Du, Yali
    Zhang, Chengqi
    IEEE TRANSACTIONS ON CYBERNETICS, 2022, 52 (10) : 11107 - 11120
12345