Ambiguity Resolution in Chinese Word Segmentation

Sun Maosong; Benjamin K. T'sou

Ambiguity Resolution in Chinese Word Segmentation

Sun Maosong
, Benjamin K. T'sou

City University of Hong Kong

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

12 Citations (Scopus)

Abstract

A new method for Chinese word segmentation named Conditional F&BMM (Forward and Backward Maximal Matching) which incorporates both bigram statistics (i.e., mutual information and difference of t-test between Chinese characters) and linguistic rules for ambiguity resolution is proposed in this paper. The key characteristics of this model are the use of: (i) statistics which can be automatically derived from any raw corpus, (ii) a rule base for disambiguation with consistency and controlled size to be built up in a systematic way. © Proceedings of the 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995.

Original language	English
Title of host publication	Proceedings of the 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995
Publisher	City University of Hong Kong Press
Pages	121-126
ISBN (Print)	9624420831, 9789624420838
Publication status	Published - 1995
Event	10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995 - Hong Kong, Hong Kong, China Duration: 27 Dec 1995 → 28 Dec 1995 https://aclanthology.org/Y95-1/

Publication series

Name	Proceedings of the 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995

Conference

Conference	10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995
Place	Hong Kong, China
City	Hong Kong
Period	27/12/95 → 28/12/95
Internet address	https://aclanthology.org/Y95-1/

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Funding

This research is supported in part by the Youth Science Foundation of Tsinghua University, Beijing, and by the Language Information Sciences Research Centre, City University of Hong Kong

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{f2416d4e367c4abda2c42b9397013468,

title = "Ambiguity Resolution in Chinese Word Segmentation",

abstract = "A new method for Chinese word segmentation named Conditional F\&BMM (Forward and Backward Maximal Matching) which incorporates both bigram statistics (i.e., mutual information and difference of t-test between Chinese characters) and linguistic rules for ambiguity resolution is proposed in this paper. The key characteristics of this model are the use of: (i) statistics which can be automatically derived from any raw corpus, (ii) a rule base for disambiguation with consistency and controlled size to be built up in a systematic way. {\textcopyright} Proceedings of the 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995.",

author = "Sun Maosong and T'sou, \{Benjamin K.\}",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].; 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995 ; Conference date: 27-12-1995 Through 28-12-1995",

year = "1995",

language = "English",

isbn = "9624420831",

series = "Proceedings of the 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995",

publisher = "City University of Hong Kong Press",

pages = "121--126",

booktitle = "Proceedings of the 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995",

address = "Hong Kong, China",

url = "https://aclanthology.org/Y95-1/",

}

Maosong, S & T'sou, BK 1995, Ambiguity Resolution in Chinese Word Segmentation. in Proceedings of the 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995. Proceedings of the 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995, City University of Hong Kong Press, pp. 121-126, 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995, Hong Kong, Hong Kong, China, 27/12/95.

Ambiguity Resolution in Chinese Word Segmentation. / Maosong, Sun; T'sou, Benjamin K.
Proceedings of the 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995. City University of Hong Kong Press, 1995. p. 121-126 (Proceedings of the 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Ambiguity Resolution in Chinese Word Segmentation

AU - Maosong, Sun

AU - T'sou, Benjamin K.

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 1995

Y1 - 1995

N2 - A new method for Chinese word segmentation named Conditional F&BMM (Forward and Backward Maximal Matching) which incorporates both bigram statistics (i.e., mutual information and difference of t-test between Chinese characters) and linguistic rules for ambiguity resolution is proposed in this paper. The key characteristics of this model are the use of: (i) statistics which can be automatically derived from any raw corpus, (ii) a rule base for disambiguation with consistency and controlled size to be built up in a systematic way. © Proceedings of the 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995.

AB - A new method for Chinese word segmentation named Conditional F&BMM (Forward and Backward Maximal Matching) which incorporates both bigram statistics (i.e., mutual information and difference of t-test between Chinese characters) and linguistic rules for ambiguity resolution is proposed in this paper. The key characteristics of this model are the use of: (i) statistics which can be automatically derived from any raw corpus, (ii) a rule base for disambiguation with consistency and controlled size to be built up in a systematic way. © Proceedings of the 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995.

UR - https://www.scopus.com/pages/publications/105042278442

UR - https://www.scopus.com/pages/publications/105042278442#tab=impact

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9624420831

SN - 9789624420838

T3 - Proceedings of the 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995

SP - 121

EP - 126

BT - Proceedings of the 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995

PB - City University of Hong Kong Press

T2 - 10th Pacific Asia Conference on Language, Information and Computation, PACLIC 1995

Y2 - 27 December 1995 through 28 December 1995

ER -

Ambiguity Resolution in Chinese Word Segmentation

Abstract

Publication series

Conference

Bibliographical note

Funding

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this