@inproceedings{wu-wang-2004-improving-domain,
title = "Improving domain-specific word alignment with a general bilingual corpus",
author = "Wu, Hua and
Wang, Haifeng",
editor = "Frederking, Robert E. and
Taylor, Kathryn B.",
booktitle = "Proceedings of the 6th Conference of the Association for Machine Translation in the Americas: Technical Papers",
month = sep # " 28 - " # oct # " 2",
year = "2004",
address = "Washington, USA",
publisher = "Springer",
url = "https://aclanthology.org/2004.amta-papers.29/",
pages = "262--271",
abstract = "In conventional word alignment methods, some employ statistical models or statistical measures, which need large-scale bilingual sentence-aligned training corpora. Others employ dictionaries to guide alignment selection. However, these methods achieve unsatisfactory alignment results when performing word alignment on a small-scale domain-specific bilingual corpus without terminological lexicons. This paper proposes an approach to improve word alignment in a specific domain, in which only a small-scale domain-specific corpus is available, by adapting the word alignment information in the general domain to the specific domain. This approach first trains two statistical word alignment models with the large-scale corpus in the general domain and the small-scale corpus in the specific domain respectively, and then improves the domain-specific word alignment with these two models. Experimental results show a significant improvement in terms of both alignment precision and recall, achieving a relative error rate reduction of 21.96{\%} as compared with state-of-the-art technologies."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-wang-2004-improving-domain">
<titleInfo>
<title>Improving domain-specific word alignment with a general bilingual corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haifeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2004-sep 28 - oct 2</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Conference of the Association for Machine Translation in the Americas: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Frederking</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kathryn</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Taylor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Springer</publisher>
<place>
<placeTerm type="text">Washington, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In conventional word alignment methods, some employ statistical models or statistical measures, which need large-scale bilingual sentence-aligned training corpora. Others employ dictionaries to guide alignment selection. However, these methods achieve unsatisfactory alignment results when performing word alignment on a small-scale domain-specific bilingual corpus without terminological lexicons. This paper proposes an approach to improve word alignment in a specific domain, in which only a small-scale domain-specific corpus is available, by adapting the word alignment information in the general domain to the specific domain. This approach first trains two statistical word alignment models with the large-scale corpus in the general domain and the small-scale corpus in the specific domain respectively, and then improves the domain-specific word alignment with these two models. Experimental results show a significant improvement in terms of both alignment precision and recall, achieving a relative error rate reduction of 21.96% as compared with state-of-the-art technologies.</abstract>
<identifier type="citekey">wu-wang-2004-improving-domain</identifier>
<location>
<url>https://aclanthology.org/2004.amta-papers.29/</url>
</location>
<part>
<date>2004-sep 28 - oct 2</date>
<extent unit="page">
<start>262</start>
<end>271</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving domain-specific word alignment with a general bilingual corpus
%A Wu, Hua
%A Wang, Haifeng
%Y Frederking, Robert E.
%Y Taylor, Kathryn B.
%S Proceedings of the 6th Conference of the Association for Machine Translation in the Americas: Technical Papers
%D 2004
%8 sep 28 oct 2
%I Springer
%C Washington, USA
%F wu-wang-2004-improving-domain
%X In conventional word alignment methods, some employ statistical models or statistical measures, which need large-scale bilingual sentence-aligned training corpora. Others employ dictionaries to guide alignment selection. However, these methods achieve unsatisfactory alignment results when performing word alignment on a small-scale domain-specific bilingual corpus without terminological lexicons. This paper proposes an approach to improve word alignment in a specific domain, in which only a small-scale domain-specific corpus is available, by adapting the word alignment information in the general domain to the specific domain. This approach first trains two statistical word alignment models with the large-scale corpus in the general domain and the small-scale corpus in the specific domain respectively, and then improves the domain-specific word alignment with these two models. Experimental results show a significant improvement in terms of both alignment precision and recall, achieving a relative error rate reduction of 21.96% as compared with state-of-the-art technologies.
%U https://aclanthology.org/2004.amta-papers.29/
%P 262-271
Markdown (Informal)
[Improving domain-specific word alignment with a general bilingual corpus](https://aclanthology.org/2004.amta-papers.29/) (Wu & Wang, AMTA 2004)
ACL