Skip navigation
  • 中文
  • English

DSpace CRIS

  • DSpace logo
  • Home
  • Research Outputs
  • Researchers
  • Organizations
  • Projects
  • Explore by
    • Research Outputs
    • Researchers
    • Organizations
    • Projects
  • Communities & Collections
  • SDGs
  • Sign in
  • 中文
  • English
  1. National Taiwan Ocean University Research Hub
  2. 電機資訊學院
  3. 資訊工程學系
Please use this identifier to cite or link to this item: http://scholars.ntou.edu.tw/handle/123456789/17876
Title: Expanding English and Chinese Dictionaries by Wikipedia Titles.
Authors: Wei-Ting Chen
Yu-Te Wang
Chuan-Jie Lin 
Keywords: dictionary expansion;proper nouns;parts-of-speech;Wikipedia
Issue Date: Sep-2019
Publisher: Association for Computational Linguistics
Journal Volume: Proceedings of the 3rd International Conference on Natural Language and Speech Processing
Start page/Pages: 107–113
Source: Department of Computer Science and Engineering National Taiwan Ocean University
Abstract: 
This paper introduces our preliminary work in dictionary expansion by adding English and Chinese Wikipedia titles along with their linguistic features. Parts-of-speech of Chinese titles are determined by the majority of heads of their Wikipedia categories. Proper noun detection in English Wikipedia is done by checking the capitalization of the titles in the content of the articles. Title alternatives will be detected beforehand. Chinese proper noun detection is done via interlanguage links and POS. The estimated accuracy of POS determination is 71.67% and the accuracy of proper noun detection is about 83.32%.
URI: http://scholars.ntou.edu.tw/handle/123456789/17876
Appears in Collections:資訊工程學系

Show full item record

Page view(s)

175
Last Week
0
Last month
0
checked on Jun 30, 2025

Google ScholarTM

Check

Related Items in TAIR


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

Explore by
  • Communities & Collections
  • Research Outputs
  • Researchers
  • Organizations
  • Projects
Build with DSpace-CRIS - Extension maintained and optimized by Logo 4SCIENCE Feedback