Context-dependent sense embedding
2016
Source Publication2016 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING, EMNLP 2016
Pages183-191
Status已发表
AbstractWord embedding has been widely studied and proven helpful in solving many natural language processing tasks. However, the ambiguity of natural language is always a problem on learning high quality word embeddings. A possible solution is sense embedding which trains embedding for each sense of words instead of each word. Some recent work on sense embedding uses context clustering methods to determine the senses of words, which is heuristic in nature. Other work creates a probabilistic model and performs word sense disambiguation and sense embedding iteratively. However, most of the previous work has the problems of learning sense embeddings based on imperfect word embeddings as well as ignoring the dependency between sense choices of neighboring words. In this paper, we propose a novel probabilistic model for sense embedding that is not based on problematic word embedding of polysemous words and takes into account the dependency between sense choices. Based on our model, we derive a dynamic programming inference algorithm and an Expectation-Maximization style unsupervised learning algorithm. The empirical studies show that our model outperforms the state-of-the-art model on a word sense induction task by a 13% relative gain.
© 2016 Association for Computational Linguistics
Conference PlaceAustin, TX, United states
Indexed ByEI
Funding ProjectNational Natural Science Foundation of China[61503248]
PublisherAssociation for Computational Linguistics (ACL)
EI Accession Number20194107499995
EI KeywordsDynamic programming ; Embeddings ; Heuristic methods ; Inference engines ; Iterative methods ; Learning algorithms ; Maximum principle
EI Classification NumberData Processing and Image Processing:723.2 ; Expert Systems:723.4.1 ; Optimization Techniques:921.5 ; Numerical Methods:921.6
Original Document TypeConference article (CA)
Document Type会议论文
Identifierhttps://kms.shanghaitech.edu.cn/handle/2MSLDSTB/29483
Collection信息科学与技术学院_PI研究组_屠可伟组
Affiliation
1.Shanghai Jiao Tong University, Shanghai, China
2.ShanghaiTech University, Shanghai, China
Recommended Citation
GB/T 7714
Qiu, Lin,Tu, Kewei,Yu, Yong. Context-dependent sense embedding[C]:Association for Computational Linguistics (ACL),2016:183-191.
Files in This Item: Download All
File Name/Size DocType Version Access License
Related Services
Usage statistics
Scholar Google
Similar articles in Scholar Google
[Qiu, Lin]'s Articles
[Tu, Kewei]'s Articles
[Yu, Yong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Qiu, Lin]'s Articles
[Tu, Kewei]'s Articles
[Yu, Yong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Qiu, Lin]'s Articles
[Tu, Kewei]'s Articles
[Yu, Yong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 10.18653@v1@D16-1018.pdf
Format: Adobe PDF
File name: 10.18653@v1@D16-1018.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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