Presentation 2000/3/16
Evaluation of Chinese Word Segmentation Method Using Inductive Learning
Zhongjian Wang, Kenji Araki, Koji Tochinai,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a word segmentation method for Chinese sentence using a common character string that occurs frequently in text, and call it common pattern. We considered that the common pattern has high probability as word. It is extracted as word candidate and registered in dictionary. Furthermore, in our method it is not necessary to prepare a dictionary and any segmentation rules for dealing with an ambiguous segmentation beforehand. We have confirmed that the proposed method is effective to Japanese word segmentation. In this paper, we describe the results of experiment for Chinese word segmentation using our proposed method. The results show that the proposed method is possible to use for multi-language word segmentation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) inductive learning / Chinese / word segmentation / common pattern / multi-language
Paper # TL99-43
Date of Issue

Conference Information
Committee TL
Conference Date 2000/3/16(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Thought and Language (TL)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Evaluation of Chinese Word Segmentation Method Using Inductive Learning
Sub Title (in English)
Keyword(1) inductive learning
Keyword(2) Chinese
Keyword(3) word segmentation
Keyword(4) common pattern
Keyword(5) multi-language
1st Author's Name Zhongjian Wang
1st Author's Affiliation Graduate School of Engineering, Hokkaido University()
2nd Author's Name Kenji Araki
2nd Author's Affiliation Graduate School of Engineering, Hokkaido University
3rd Author's Name Koji Tochinai
3rd Author's Affiliation Graduate School of Engineering, Hokkaido University
Date 2000/3/16
Paper # TL99-43
Volume (vol) vol.99
Number (no) 691
Page pp.pp.-
#Pages 7
Date of Issue