微信服务号

微信订阅号

2025-4-13- 3
Home > Archive>Volume 27, Issue 11, 2016 >2691-2700. DOI:10.13328/j.cnki.jos.004873
PDF HTML XML Export Cite reminder
Neural-Based Combinatory Categorical Grammar Supertagging
Author:
Affiliation:

Fund Project:

National Natural Science Foundation of China (61333018); Strategic Priority Research Program of the Chinese Academy of Sciences (XDB02070007)

  • Article
    • | |
  • Metrics
    • |
  • Reference
    • |
  • Related
    • |
  • Cited by
    • | |
  • Comments
    Abstract:

    As a sub-task for combinatory categorical grammar (CCG) based parsing, categorical tagging can improve parsing efficiency and accuracy. While traditional maximum entropy model solves this problem by designing meaningful feature templates, neural network can extract features automatically based on distributed representations. This paper proposes a neural categorical tagging model with two improvements. First, word embedding layer is extended with a part-of-speech embedding layer and a category embedding layer, which facilitates learning their distributed representations jointly by the back-propagation algorithm. Secondly, a beam search is used in the decoding to capture the dependencies among tags. These two improvements make the proposed model more accurate than the state-of-art maximum entropy based tagger (up to 1%).

    Reference
    Related
    Cited by
Get Citation

吴惠甲,张家俊,宗成庆.一种神经范畴标注模型.软件学报,2016,27(11):2691-2700

Copy
Share
Article Metrics
  • Abstract:2516
  • PDF: 4163
  • HTML: 1420
  • Cited by: 0
History
  • Received:March 17,2015
  • Revised:June 24,2015
  • Online: November 02,2016
Links:Institute of Software, CASChina Computer FederationCASNSFC
You are the first2034787Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address：4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code：100190
Phone：010-62562563 Fax：010-62562533 Email：jos@iscas.ac.cn
Technical Support：Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063