Dependency grammar induction with neural lexicalization and big training data
Han, Wenjuan; Jiang, Yong; Tu, Kewei
2017
Source Publication2017 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING, EMNLP 2017
Pages1683-1688
Status已发表
AbstractWe 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.
Conference PlaceCopenhagen, Denmark
Indexed ByEI
Funding ProjectNational Natural Science Foundation of China[61503248]
PublisherAssociation for Computational Linguistics (ACL)
EI Accession Number20194207538744
EI KeywordsComputational grammars ; Linguistics
EI Classification NumberComputer Theory, Includes Formal Logic, Automata Theory, Switching Theory, Programming Theory:721.1 ; Data Processing and Image Processing:723.2
Original Document TypeConference article (CA)
Document Type会议论文
Identifierhttps://kms.shanghaitech.edu.cn/handle/2MSLDSTB/29237
Collection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
AffiliationSchool of Information Science and Technology, ShanghaiTech University, Shanghai, China
First Author AffilicationSchool of Information Science and Technology
First Signature AffilicationSchool of Information Science and Technology
Recommended Citation
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.
Files in This Item: Download All
File Name/Size DocType Version Access License
10.18653@v1@D17-1176(1054KB)会议论文出版稿开放获取UnknownView Download
10.18653@v1@D17-1176(1054KB)会议论文出版稿开放获取UnknownView Download
Related Services
Usage statistics
Scholar Google
Similar articles in Scholar Google
[Han, Wenjuan]'s Articles
[Jiang, Yong]'s Articles
[Tu, Kewei]'s Articles
Baidu academic
Similar articles in Baidu academic
[Han, Wenjuan]'s Articles
[Jiang, Yong]'s Articles
[Tu, Kewei]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Han, Wenjuan]'s Articles
[Jiang, Yong]'s Articles
[Tu, Kewei]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 10.18653@v1@D17-1176.pdf
Format: Adobe PDF
File name: 10.18653@v1@D17-1176.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.