@inproceedings{hazem-daille-2016-bilingual,
title = "Bilingual Lexicon Extraction at the Morpheme Level Using Distributional Analysis",
author = "Hazem, Amir and
Daille, B{\'e}atrice",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1496",
pages = "3110--3115",
abstract = "Bilingual lexicon extraction from comparable corpora is usually based on distributional methods when dealing with single word terms (SWT). These methods often treat SWT as single tokens without considering their compositional property. However, many SWT are compositional (composed of roots and affixes) and this information, if taken into account can be very useful to match translational pairs, especially for infrequent terms where distributional methods often fail. For instance, the English compound \textit{xenograft} which is composed of the root \textit{xeno} and the lexeme \textit{graft} can be translated into French compositionally by aligning each of its elements (\textit{xeno} with \textit{x{\'e}no} and \textit{graft} with \textit{greffe}) resulting in the translation: \textit{x{\'e}nogreffe}. In this paper, we experiment several distributional modellings at the morpheme level that we apply to perform compositional translation to a subset of French and English compounds. We show promising results using distributional analysis at the root and affix levels. We also show that the adapted approach significantly improve bilingual lexicon extraction from comparable corpora compared to the approach at the word level.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hazem-daille-2016-bilingual">
<titleInfo>
<title>Bilingual Lexicon Extraction at the Morpheme Level Using Distributional Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Hazem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Béatrice</namePart>
<namePart type="family">Daille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Bilingual lexicon extraction from comparable corpora is usually based on distributional methods when dealing with single word terms (SWT). These methods often treat SWT as single tokens without considering their compositional property. However, many SWT are compositional (composed of roots and affixes) and this information, if taken into account can be very useful to match translational pairs, especially for infrequent terms where distributional methods often fail. For instance, the English compound xenograft which is composed of the root xeno and the lexeme graft can be translated into French compositionally by aligning each of its elements (xeno with xéno and graft with greffe) resulting in the translation: xénogreffe. In this paper, we experiment several distributional modellings at the morpheme level that we apply to perform compositional translation to a subset of French and English compounds. We show promising results using distributional analysis at the root and affix levels. We also show that the adapted approach significantly improve bilingual lexicon extraction from comparable corpora compared to the approach at the word level.</abstract>
<identifier type="citekey">hazem-daille-2016-bilingual</identifier>
<location>
<url>https://aclanthology.org/L16-1496</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3110</start>
<end>3115</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bilingual Lexicon Extraction at the Morpheme Level Using Distributional Analysis
%A Hazem, Amir
%A Daille, Béatrice
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F hazem-daille-2016-bilingual
%X Bilingual lexicon extraction from comparable corpora is usually based on distributional methods when dealing with single word terms (SWT). These methods often treat SWT as single tokens without considering their compositional property. However, many SWT are compositional (composed of roots and affixes) and this information, if taken into account can be very useful to match translational pairs, especially for infrequent terms where distributional methods often fail. For instance, the English compound xenograft which is composed of the root xeno and the lexeme graft can be translated into French compositionally by aligning each of its elements (xeno with xéno and graft with greffe) resulting in the translation: xénogreffe. In this paper, we experiment several distributional modellings at the morpheme level that we apply to perform compositional translation to a subset of French and English compounds. We show promising results using distributional analysis at the root and affix levels. We also show that the adapted approach significantly improve bilingual lexicon extraction from comparable corpora compared to the approach at the word level.
%U https://aclanthology.org/L16-1496
%P 3110-3115
Markdown (Informal)
[Bilingual Lexicon Extraction at the Morpheme Level Using Distributional Analysis](https://aclanthology.org/L16-1496) (Hazem & Daille, LREC 2016)
ACL