Effects of term segmentation on Chinese/English cross-language information retrieval

Douglas W. Oard; Jianqiang Wang

doi:10.1109/SPIRE.1999.796590

Effects of term segmentation on Chinese/English cross-language information retrieval

Douglas W. Oard
, Jianqiang Wang

Information Science

University of Maryland, College Park

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Scopus citations

Abstract

The majority of recent Cross-Language Information Retrieval (CLIR) research has focused on European languages. CLIR problems that involve East Asian languages such as Chinese introduce additional challenges, because written Chinese texts lack boundaries between terms. The paper examines three Chinese segmentation techniques in combination with two variants of dictionary-based Chinese to English query translation. The results indicate that failure to segment terms, particularly technical terms and names, can have a cascading effect that reduces retrieval effectiveness. Task-tuned segmentation algorithms and alternative term weighting strategies are suggested as productive directions for future work.

Original language	English
Title of host publication	String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	149-157
Number of pages	9
ISBN (Electronic)	0769502687, 9780769502687
DOIs	https://doi.org/10.1109/SPIRE.1999.796590
State	Published - 1999
Event	1999 String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999 - Cancun, Mexico Duration: Sep 22 1999 → Sep 24 1999

Publication series

Name	String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999

Conference

Conference	1999 String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999
Country/Territory	Mexico
City	Cancun
Period	09/22/99 → 09/24/99

Access to Document

10.1109/SPIRE.1999.796590

Cite this

Oard, D. W., & Wang, J. (1999). Effects of term segmentation on Chinese/English cross-language information retrieval. In String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999 (pp. 149-157). Article 796590 (String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SPIRE.1999.796590

Oard, Douglas W. ; Wang, Jianqiang. / Effects of term segmentation on Chinese/English cross-language information retrieval. String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999. Institute of Electrical and Electronics Engineers Inc., 1999. pp. 149-157 (String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999).

@inproceedings{7f7f8253d01c4c7ea89b510c87e7b02d,

title = "Effects of term segmentation on Chinese/English cross-language information retrieval",

abstract = "The majority of recent Cross-Language Information Retrieval (CLIR) research has focused on European languages. CLIR problems that involve East Asian languages such as Chinese introduce additional challenges, because written Chinese texts lack boundaries between terms. The paper examines three Chinese segmentation techniques in combination with two variants of dictionary-based Chinese to English query translation. The results indicate that failure to segment terms, particularly technical terms and names, can have a cascading effect that reduces retrieval effectiveness. Task-tuned segmentation algorithms and alternative term weighting strategies are suggested as productive directions for future work.",

author = "Oard, \{Douglas W.\} and Jianqiang Wang",

note = "Publisher Copyright: {\textcopyright} 1999 IEEE.; 1999 String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999 ; Conference date: 22-09-1999 Through 24-09-1999",

year = "1999",

doi = "10.1109/SPIRE.1999.796590",

language = "English",

series = "String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "149--157",

booktitle = "String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999",

address = "United States",

}

Oard, DW & Wang, J 1999, Effects of term segmentation on Chinese/English cross-language information retrieval. in String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999., 796590, String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999, Institute of Electrical and Electronics Engineers Inc., pp. 149-157, 1999 String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999, Cancun, Mexico, 09/22/99. https://doi.org/10.1109/SPIRE.1999.796590

Effects of term segmentation on Chinese/English cross-language information retrieval. / Oard, Douglas W.; Wang, Jianqiang.
String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999. Institute of Electrical and Electronics Engineers Inc., 1999. p. 149-157 796590 (String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Effects of term segmentation on Chinese/English cross-language information retrieval

AU - Oard, Douglas W.

AU - Wang, Jianqiang

PY - 1999

Y1 - 1999

N2 - The majority of recent Cross-Language Information Retrieval (CLIR) research has focused on European languages. CLIR problems that involve East Asian languages such as Chinese introduce additional challenges, because written Chinese texts lack boundaries between terms. The paper examines three Chinese segmentation techniques in combination with two variants of dictionary-based Chinese to English query translation. The results indicate that failure to segment terms, particularly technical terms and names, can have a cascading effect that reduces retrieval effectiveness. Task-tuned segmentation algorithms and alternative term weighting strategies are suggested as productive directions for future work.

AB - The majority of recent Cross-Language Information Retrieval (CLIR) research has focused on European languages. CLIR problems that involve East Asian languages such as Chinese introduce additional challenges, because written Chinese texts lack boundaries between terms. The paper examines three Chinese segmentation techniques in combination with two variants of dictionary-based Chinese to English query translation. The results indicate that failure to segment terms, particularly technical terms and names, can have a cascading effect that reduces retrieval effectiveness. Task-tuned segmentation algorithms and alternative term weighting strategies are suggested as productive directions for future work.

UR - https://www.scopus.com/pages/publications/85029365523

U2 - 10.1109/SPIRE.1999.796590

DO - 10.1109/SPIRE.1999.796590

M3 - Conference contribution

AN - SCOPUS:85029365523

T3 - String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999

SP - 149

EP - 157

BT - String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1999 String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999

Y2 - 22 September 1999 through 24 September 1999

ER -

Oard DW, Wang J. Effects of term segmentation on Chinese/English cross-language information retrieval. In String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999. Institute of Electrical and Electronics Engineers Inc. 1999. p. 149-157. 796590. (String Processing and Information Retrieval Symposium and International Workshop on Groupware, SPIRE 1999 and CRIWG 1999). doi: 10.1109/SPIRE.1999.796590

Effects of term segmentation on Chinese/English cross-language information retrieval

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this