@inproceedings{hearne-etal-2008-comparing,
title = "Comparing Constituency and Dependency Representations for {SMT} Phrase-Extraction",
author = "Hearne, Mary and
Ozdowska, Sylwia and
Tinsley, John",
editor = "B{\'e}chet, Fr{\'e}d{\'e}ric and
Bonastre, Jean-Francois",
booktitle = "Actes de la 15{\`e}me conf{\'e}rence sur le Traitement Automatique des Langues Naturelles. Articles courts",
month = jun,
year = "2008",
address = "Avignon, France",
publisher = "ATALA",
url = "https://aclanthology.org/2008.jeptalnrecital-court.14",
pages = "131--140",
abstract = "We consider the value of replacing and/or combining string-basedmethods with syntax-based methods for phrase-based statistical machine translation (PBSMT), and we also consider the relative merits of using constituency-annotated vs. dependency-annotated training data. We automatically derive two subtree-aligned treebanks, dependency-based and constituency-based, from a parallel English{--}French corpus and extract syntactically motivated word- and phrase-pairs. We automatically measure PB-SMT quality. The results show that combining string-based and syntax-based word- and phrase-pairs can improve translation quality irrespective of the type of syntactic annotation. Furthermore, using dependency annotation yields greater translation quality than constituency annotation for PB-SMT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hearne-etal-2008-comparing">
<titleInfo>
<title>Comparing Constituency and Dependency Representations for SMT Phrase-Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Hearne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sylwia</namePart>
<namePart type="family">Ozdowska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Tinsley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Actes de la 15ème conférence sur le Traitement Automatique des Langues Naturelles. Articles courts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-Francois</namePart>
<namePart type="family">Bonastre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ATALA</publisher>
<place>
<placeTerm type="text">Avignon, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We consider the value of replacing and/or combining string-basedmethods with syntax-based methods for phrase-based statistical machine translation (PBSMT), and we also consider the relative merits of using constituency-annotated vs. dependency-annotated training data. We automatically derive two subtree-aligned treebanks, dependency-based and constituency-based, from a parallel English–French corpus and extract syntactically motivated word- and phrase-pairs. We automatically measure PB-SMT quality. The results show that combining string-based and syntax-based word- and phrase-pairs can improve translation quality irrespective of the type of syntactic annotation. Furthermore, using dependency annotation yields greater translation quality than constituency annotation for PB-SMT.</abstract>
<identifier type="citekey">hearne-etal-2008-comparing</identifier>
<location>
<url>https://aclanthology.org/2008.jeptalnrecital-court.14</url>
</location>
<part>
<date>2008-06</date>
<extent unit="page">
<start>131</start>
<end>140</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing Constituency and Dependency Representations for SMT Phrase-Extraction
%A Hearne, Mary
%A Ozdowska, Sylwia
%A Tinsley, John
%Y Béchet, Frédéric
%Y Bonastre, Jean-Francois
%S Actes de la 15ème conférence sur le Traitement Automatique des Langues Naturelles. Articles courts
%D 2008
%8 June
%I ATALA
%C Avignon, France
%F hearne-etal-2008-comparing
%X We consider the value of replacing and/or combining string-basedmethods with syntax-based methods for phrase-based statistical machine translation (PBSMT), and we also consider the relative merits of using constituency-annotated vs. dependency-annotated training data. We automatically derive two subtree-aligned treebanks, dependency-based and constituency-based, from a parallel English–French corpus and extract syntactically motivated word- and phrase-pairs. We automatically measure PB-SMT quality. The results show that combining string-based and syntax-based word- and phrase-pairs can improve translation quality irrespective of the type of syntactic annotation. Furthermore, using dependency annotation yields greater translation quality than constituency annotation for PB-SMT.
%U https://aclanthology.org/2008.jeptalnrecital-court.14
%P 131-140
Markdown (Informal)
[Comparing Constituency and Dependency Representations for SMT Phrase-Extraction](https://aclanthology.org/2008.jeptalnrecital-court.14) (Hearne et al., JEP/TALN/RECITAL 2008)
ACL