ShanghaiTech University Knowledge Management System
Context-dependent sense embedding | |
2016 | |
Source Publication | 2016 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING, EMNLP 2016
![]() |
Pages | 183-191 |
Status | 已发表 |
Abstract | Word 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 Place | Austin, TX, United states |
Indexed By | EI |
Funding Project | National Natural Science Foundation of China[61503248] |
Publisher | Association for Computational Linguistics (ACL) |
EI Accession Number | 20194107499995 |
EI Keywords | Dynamic programming ; Embeddings ; Heuristic methods ; Inference engines ; Iterative methods ; Learning algorithms ; Maximum principle |
EI Classification Number | Data Processing and Image Processing:723.2 ; Expert Systems:723.4.1 ; Optimization Techniques:921.5 ; Numerical Methods:921.6 |
Original Document Type | Conference article (CA) |
Document Type | 会议论文 |
Identifier | https://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 |
Edit Comment
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.