Generating patterns for extracting Chinese-Korean named entity translations from the Web

Chih Hao Yeh; Wei Chi Tsai; Yu Chun Wang; Richard Tzong Han Tsai

Generating patterns for extracting Chinese-Korean named entity translations from the Web

Chih Hao Yeh, Wei Chi Tsai, Yu Chun Wang, Richard Tzong Han Tsai

資訊工程學系

研究成果: 會議貢獻類型 › 會議論文 › 同行評審

摘要

One of the main difficulties in Chinese-Korean cross-language information retrieval is to translate named entities (NE) in queries. Unlike common words, most NE's are not found in bilingual dictionaries. This paper presents a pattern-based method of finding NE translations online. The most important feature of our system is that patterns are generated and weighed automatically, saving considerable human effort. Our experimental data consists of 160 Chinese-Korean NE pairs selected from Wikipedia in five domains. Our approach can achieve a very high MAP of 0.84, which demonstrates our system's practicability.

原文	???core.languages.en_GB???
頁面	366-372
頁數	7
出版狀態	已出版 - 2008
事件	20th Conference on Computational Linguistics and Speech Processing, ROCLING 2008 - Taipei, Taiwan 持續時間: 4 9月 2008 → 5 9月 2008

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	20th Conference on Computational Linguistics and Speech Processing, ROCLING 2008
國家/地區	Taiwan
城市	Taipei
期間	4/09/08 → 5/09/08

引用此

@conference{107f0659611e4f7bbb3495d3590b19f8,

title = "Generating patterns for extracting Chinese-Korean named entity translations from the Web",

abstract = "One of the main difficulties in Chinese-Korean cross-language information retrieval is to translate named entities (NE) in queries. Unlike common words, most NE's are not found in bilingual dictionaries. This paper presents a pattern-based method of finding NE translations online. The most important feature of our system is that patterns are generated and weighed automatically, saving considerable human effort. Our experimental data consists of 160 Chinese-Korean NE pairs selected from Wikipedia in five domains. Our approach can achieve a very high MAP of 0.84, which demonstrates our system's practicability.",

keywords = "Chinese-Korean named entity translation, Pattern, The Web",

author = "Yeh, {Chih Hao} and Tsai, {Wei Chi} and Wang, {Yu Chun} and Tsai, {Richard Tzong Han}",

year = "2008",

language = "???core.languages.en_GB???",

pages = "366--372",

note = "20th Conference on Computational Linguistics and Speech Processing, ROCLING 2008 ; Conference date: 04-09-2008 Through 05-09-2008",

}

TY - CONF

T1 - Generating patterns for extracting Chinese-Korean named entity translations from the Web

AU - Yeh, Chih Hao

AU - Tsai, Wei Chi

AU - Wang, Yu Chun

AU - Tsai, Richard Tzong Han

PY - 2008

Y1 - 2008

N2 - One of the main difficulties in Chinese-Korean cross-language information retrieval is to translate named entities (NE) in queries. Unlike common words, most NE's are not found in bilingual dictionaries. This paper presents a pattern-based method of finding NE translations online. The most important feature of our system is that patterns are generated and weighed automatically, saving considerable human effort. Our experimental data consists of 160 Chinese-Korean NE pairs selected from Wikipedia in five domains. Our approach can achieve a very high MAP of 0.84, which demonstrates our system's practicability.

AB - One of the main difficulties in Chinese-Korean cross-language information retrieval is to translate named entities (NE) in queries. Unlike common words, most NE's are not found in bilingual dictionaries. This paper presents a pattern-based method of finding NE translations online. The most important feature of our system is that patterns are generated and weighed automatically, saving considerable human effort. Our experimental data consists of 160 Chinese-Korean NE pairs selected from Wikipedia in five domains. Our approach can achieve a very high MAP of 0.84, which demonstrates our system's practicability.

KW - Chinese-Korean named entity translation

KW - Pattern

KW - The Web

UR - http://www.scopus.com/inward/record.url?scp=84883120824&partnerID=8YFLogxK

M3 - 會議論文

AN - SCOPUS:84883120824

SP - 366

EP - 372

T2 - 20th Conference on Computational Linguistics and Speech Processing, ROCLING 2008

Y2 - 4 September 2008 through 5 September 2008

ER -

Generating patterns for extracting Chinese-Korean named entity translations from the Web

摘要

???event.eventtypes.event.conference???

指紋

引用此