@inproceedings{dorr-etal-2002-duster,
title = "{DUST}er: a method for unraveling cross-language divergences for statistical word-level alignment",
author = "Dorr, Bonnie and
Pearl, Lisa and
Hwa, Rebecca and
Habash, Nizar",
booktitle = "Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: Technical Papers",
month = oct # " 8-12",
year = "2002",
address = "Tiburon, USA",
publisher = "Springer",
url = "https://link.springer.com/chapter/10.1007/3-540-45820-4_4",
pages = "31--43",
abstract = "The frequent occurrence of divergenceS{---}structural differences between languages{---}presents a great challenge for statistical word-level alignment. In this paper, we introduce DUSTer, a method for systematically identifying common divergence types and transforming an English sentence structure to bear a closer resemblance to that of another language. Our ultimate goal is to enable more accurate alignment and projection of dependency trees in another language without requiring any training on dependency-tree data in that language. We present an empirical analysis comparing the complexities of performing word-level alignments with and without divergence handling. Our results suggest that our approach facilitates word-level alignment, particularly for sentence pairs containing divergences.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dorr-etal-2002-duster">
<titleInfo>
<title>DUSTer: a method for unraveling cross-language divergences for statistical word-level alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Dorr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Pearl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Hwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2002-oct" 8-12"</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: Technical Papers</title>
</titleInfo>
<originInfo>
<publisher>Springer</publisher>
<place>
<placeTerm type="text">Tiburon, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The frequent occurrence of divergenceS—structural differences between languages—presents a great challenge for statistical word-level alignment. In this paper, we introduce DUSTer, a method for systematically identifying common divergence types and transforming an English sentence structure to bear a closer resemblance to that of another language. Our ultimate goal is to enable more accurate alignment and projection of dependency trees in another language without requiring any training on dependency-tree data in that language. We present an empirical analysis comparing the complexities of performing word-level alignments with and without divergence handling. Our results suggest that our approach facilitates word-level alignment, particularly for sentence pairs containing divergences.</abstract>
<identifier type="citekey">dorr-etal-2002-duster</identifier>
<location>
<url>https://link.springer.com/chapter/10.1007/3-540-45820-4_4</url>
</location>
<part>
<date>2002-oct" 8-12"</date>
<extent unit="page">
<start>31</start>
<end>43</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DUSTer: a method for unraveling cross-language divergences for statistical word-level alignment
%A Dorr, Bonnie
%A Pearl, Lisa
%A Hwa, Rebecca
%A Habash, Nizar
%S Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: Technical Papers
%D 2002
%8 oct" 8 12"
%I Springer
%C Tiburon, USA
%F dorr-etal-2002-duster
%X The frequent occurrence of divergenceS—structural differences between languages—presents a great challenge for statistical word-level alignment. In this paper, we introduce DUSTer, a method for systematically identifying common divergence types and transforming an English sentence structure to bear a closer resemblance to that of another language. Our ultimate goal is to enable more accurate alignment and projection of dependency trees in another language without requiring any training on dependency-tree data in that language. We present an empirical analysis comparing the complexities of performing word-level alignments with and without divergence handling. Our results suggest that our approach facilitates word-level alignment, particularly for sentence pairs containing divergences.
%U https://link.springer.com/chapter/10.1007/3-540-45820-4_4
%P 31-43
Markdown (Informal)
[DUSTer: a method for unraveling cross-language divergences for statistical word-level alignment](https://link.springer.com/chapter/10.1007/3-540-45820-4_4) (Dorr et al., AMTA 2002)
ACL