Improving translation of unknown proper names using a hybrid web-based translation extraction method

Min Shiang Shia, Jiun Hung Lin, Scott Yu, Wen-Hsiang Lu

研究成果: Paper

2 引文 (Scopus)

摘要

Recently, we have proposed several effective Web-based term translation extraction methods exploring Web resources to deal with translation of Web query terms. However, many unknown proper names in Web queries are still difficult to be translated by using our previous Web-based term translation extraction methods. Therefore, in this paper we propose a new hybrid translation extraction method, which combines our pervious Web-based term translation extraction method and a new Web-based transliteration method in order to improve translation of unknown proper names. In addition, to efficiently construct a good quality transliteration model, we also present a mixed-syllable-mapping transliteration model and a Web-based semi-supervised learning algorithm to explore search-result pages further for collecting large amounts of English-Chinese transliteration pairs from the Web.

原文English
出版狀態Published - 2005 十二月 1
事件17th Conference on Computational Linguistics and Speech Processing, ROCLING 2005 - Tainan, Taiwan
持續時間: 2005 九月 152005 九月 16

Other

Other17th Conference on Computational Linguistics and Speech Processing, ROCLING 2005
國家Taiwan
城市Tainan
期間05-09-1505-09-16

指紋

Names
Proper Names
World Wide Web
Transliteration

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Speech and Hearing

引用此文

Shia, M. S., Lin, J. H., Yu, S., & Lu, W-H. (2005). Improving translation of unknown proper names using a hybrid web-based translation extraction method. 論文發表於 17th Conference on Computational Linguistics and Speech Processing, ROCLING 2005, Tainan, Taiwan.
Shia, Min Shiang ; Lin, Jiun Hung ; Yu, Scott ; Lu, Wen-Hsiang. / Improving translation of unknown proper names using a hybrid web-based translation extraction method. 論文發表於 17th Conference on Computational Linguistics and Speech Processing, ROCLING 2005, Tainan, Taiwan.
@conference{879ef5f060e247828266d9bf5b1415b2,
title = "Improving translation of unknown proper names using a hybrid web-based translation extraction method",
abstract = "Recently, we have proposed several effective Web-based term translation extraction methods exploring Web resources to deal with translation of Web query terms. However, many unknown proper names in Web queries are still difficult to be translated by using our previous Web-based term translation extraction methods. Therefore, in this paper we propose a new hybrid translation extraction method, which combines our pervious Web-based term translation extraction method and a new Web-based transliteration method in order to improve translation of unknown proper names. In addition, to efficiently construct a good quality transliteration model, we also present a mixed-syllable-mapping transliteration model and a Web-based semi-supervised learning algorithm to explore search-result pages further for collecting large amounts of English-Chinese transliteration pairs from the Web.",
author = "Shia, {Min Shiang} and Lin, {Jiun Hung} and Scott Yu and Wen-Hsiang Lu",
year = "2005",
month = "12",
day = "1",
language = "English",
note = "17th Conference on Computational Linguistics and Speech Processing, ROCLING 2005 ; Conference date: 15-09-2005 Through 16-09-2005",

}

Shia, MS, Lin, JH, Yu, S & Lu, W-H 2005, 'Improving translation of unknown proper names using a hybrid web-based translation extraction method', 論文發表於 17th Conference on Computational Linguistics and Speech Processing, ROCLING 2005, Tainan, Taiwan, 05-09-15 - 05-09-16.

Improving translation of unknown proper names using a hybrid web-based translation extraction method. / Shia, Min Shiang; Lin, Jiun Hung; Yu, Scott; Lu, Wen-Hsiang.

2005. 論文發表於 17th Conference on Computational Linguistics and Speech Processing, ROCLING 2005, Tainan, Taiwan.

研究成果: Paper

TY - CONF

T1 - Improving translation of unknown proper names using a hybrid web-based translation extraction method

AU - Shia, Min Shiang

AU - Lin, Jiun Hung

AU - Yu, Scott

AU - Lu, Wen-Hsiang

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Recently, we have proposed several effective Web-based term translation extraction methods exploring Web resources to deal with translation of Web query terms. However, many unknown proper names in Web queries are still difficult to be translated by using our previous Web-based term translation extraction methods. Therefore, in this paper we propose a new hybrid translation extraction method, which combines our pervious Web-based term translation extraction method and a new Web-based transliteration method in order to improve translation of unknown proper names. In addition, to efficiently construct a good quality transliteration model, we also present a mixed-syllable-mapping transliteration model and a Web-based semi-supervised learning algorithm to explore search-result pages further for collecting large amounts of English-Chinese transliteration pairs from the Web.

AB - Recently, we have proposed several effective Web-based term translation extraction methods exploring Web resources to deal with translation of Web query terms. However, many unknown proper names in Web queries are still difficult to be translated by using our previous Web-based term translation extraction methods. Therefore, in this paper we propose a new hybrid translation extraction method, which combines our pervious Web-based term translation extraction method and a new Web-based transliteration method in order to improve translation of unknown proper names. In addition, to efficiently construct a good quality transliteration model, we also present a mixed-syllable-mapping transliteration model and a Web-based semi-supervised learning algorithm to explore search-result pages further for collecting large amounts of English-Chinese transliteration pairs from the Web.

UR - http://www.scopus.com/inward/record.url?scp=84882935617&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84882935617&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84882935617

ER -

Shia MS, Lin JH, Yu S, Lu W-H. Improving translation of unknown proper names using a hybrid web-based translation extraction method. 2005. 論文發表於 17th Conference on Computational Linguistics and Speech Processing, ROCLING 2005, Tainan, Taiwan.