Dependency grammar induction with neural lexicalization and big training data

	Dependency grammar induction with neural lexicalization and big training data
	Han, Wenjuan; Jiang, Yong; Tu, Kewei
	2017
会议录名称	2017 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING, EMNLP 2017
页码	1683-1688
发表状态	已发表
摘要	We study the impact of big models (in terms of the degree of lexicalization) and big data (in terms of the training corpus size) on dependency grammar induction. We experimented with L-DMV, a lexicalized version of Dependency Model with Valence (Klein and Manning, 2004) and L-NDMV, our lexicalized extension of the Neural Dependency Model with Valence (Jiang et al., 2016). We find that L-DMV only benefits from very small degrees of lexicalization and moderate sizes of training corpora. L-NDMV can benefit from big training data and lexicalization of greater degrees, especially when enhanced with good model initialization, and it achieves a result that is competitive with the current state-of-the-art. © 2017 Association for Computational Linguistics.
会议地点	Copenhagen, Denmark
收录类别	EI
资助项目	National Natural Science Foundation of China[61503248]
出版者	Association for Computational Linguistics (ACL)
EI入藏号	20194207538744
EI主题词	Computational grammars ; Linguistics
EI分类号	Computer Theory, Includes Formal Logic, Automata Theory, Switching Theory, Programming Theory:721.1 ; Data Processing and Image Processing:723.2
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/29237
专题	信息科学与技术学院_博士生信息科学与技术学院_PI研究组_屠可伟组
作者单位	School of Information Science and Technology, ShanghaiTech University, Shanghai, China
第一作者单位	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	Han, Wenjuan,Jiang, Yong,Tu, Kewei. Dependency grammar induction with neural lexicalization and big training data[C]:Association for Computational Linguistics (ACL),2017:1683-1688.