An Investigation of Potential Function Designs for Neural CRF

doi:/

	An Investigation of Potential Function Designs for Neural CRF
	Hu, Zechuan1,2,3,4 ; Jiang, Yong 5; Bach, Nguyen 5; Wang, Tao 5; Huang, Fei 5; Tu, Kewei1,2,3,4
	2020-11
会议录名称	FINDINGS OF EMNLP, 2020
卷号	Findings of the Association for Computational Linguistics: EMNLP 2020
页码	2600–2609
发表状态	已发表
DOI	/
摘要	The neural linear-chain CRF model is one of the most widely-used approach to sequence labeling. In this paper, we investigate a series of increasingly expressive potential functions for neural CRF models, which not only integrate the emission and transition functions, but also explicitly take the representations of the contextual words as input. Our extensive experiments show that the decomposed quadrilinear potential function based on the vector representations of two neighboring labels and two neighboring words consistently achieves the best performance.
关键词	Contextual words Emission functions Function designs Linear chain Performance Potential function Quadrilinear Sequence Labeling Transition functions Vector representations
会议名称	Findings of the Association for Computational Linguistics, ACL 2020: EMNLP 2020
会议地点	Virtual, Online
会议日期	November 16, 2020 - November 20, 2020
收录类别	EI
语种	英语
出版者	Association for Computational Linguistics (ACL)
EI入藏号	20214511116220
EI主题词	Computational linguistics
EI分类号	721.1 Computer Theory, Includes Formal Logic, Automata Theory, Switching Theory, Programming Theory
原始文献类型	Conference article (CA)
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/124043
专题	信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_屠可伟组
通讯作者	Jiang, Yong; Tu, Kewei
作者单位	1.School of Information Science and Technology, ShanghaiTech University 2.Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences 3.University of Chinese Academy of Sciences 4.Shanghai Engineering Research Center of Intelligent Vision and Imaging 5.DAMO Academy, Alibaba Group
第一作者单位	信息科学与技术学院
通讯作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Hu, Zechuan,Jiang, Yong,Bach, Nguyen,et al. An Investigation of Potential Function Designs for Neural CRF[C]:Association for Computational Linguistics (ACL),2020:2600–2609.