@inproceedings{adjali-etal-2022-building,
title = "Building Comparable Corpora for Assessing Multi-Word Term Alignment",
author = "Adjali, Omar and
Morin, Emmanuel and
Zweigenbaum, Pierre",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.332",
pages = "3103--3112",
abstract = "Recent work has demonstrated the importance of dealing with Multi-Word Terms (MWTs) in several Natural Language Processing applications. In particular, MWTs pose serious challenges for alignment and machine translation systems because of their syntactic and semantic properties. Thus, developing algorithms that handle MWTs is becoming essential for many NLP tasks. However, the availability of bilingual and more generally multi-lingual resources is limited, especially for low-resourced languages and in specialized domains. In this paper, we propose an approach for building comparable corpora and bilingual term dictionaries that help evaluate bilingual term alignment in comparable corpora. To that aim, we exploit parallel corpora to perform automatic bilingual MWT extraction and comparable corpus construction. Parallel information helps to align bilingual MWTs and makes it easier to build comparable specialized sub-corpora. Experimental validation on an existing dataset and on manually annotated data shows the interest of the proposed methodology.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adjali-etal-2022-building">
<titleInfo>
<title>Building Comparable Corpora for Assessing Multi-Word Term Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Adjali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Morin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Zweigenbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent work has demonstrated the importance of dealing with Multi-Word Terms (MWTs) in several Natural Language Processing applications. In particular, MWTs pose serious challenges for alignment and machine translation systems because of their syntactic and semantic properties. Thus, developing algorithms that handle MWTs is becoming essential for many NLP tasks. However, the availability of bilingual and more generally multi-lingual resources is limited, especially for low-resourced languages and in specialized domains. In this paper, we propose an approach for building comparable corpora and bilingual term dictionaries that help evaluate bilingual term alignment in comparable corpora. To that aim, we exploit parallel corpora to perform automatic bilingual MWT extraction and comparable corpus construction. Parallel information helps to align bilingual MWTs and makes it easier to build comparable specialized sub-corpora. Experimental validation on an existing dataset and on manually annotated data shows the interest of the proposed methodology.</abstract>
<identifier type="citekey">adjali-etal-2022-building</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.332</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3103</start>
<end>3112</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building Comparable Corpora for Assessing Multi-Word Term Alignment
%A Adjali, Omar
%A Morin, Emmanuel
%A Zweigenbaum, Pierre
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F adjali-etal-2022-building
%X Recent work has demonstrated the importance of dealing with Multi-Word Terms (MWTs) in several Natural Language Processing applications. In particular, MWTs pose serious challenges for alignment and machine translation systems because of their syntactic and semantic properties. Thus, developing algorithms that handle MWTs is becoming essential for many NLP tasks. However, the availability of bilingual and more generally multi-lingual resources is limited, especially for low-resourced languages and in specialized domains. In this paper, we propose an approach for building comparable corpora and bilingual term dictionaries that help evaluate bilingual term alignment in comparable corpora. To that aim, we exploit parallel corpora to perform automatic bilingual MWT extraction and comparable corpus construction. Parallel information helps to align bilingual MWTs and makes it easier to build comparable specialized sub-corpora. Experimental validation on an existing dataset and on manually annotated data shows the interest of the proposed methodology.
%U https://aclanthology.org/2022.lrec-1.332
%P 3103-3112
Markdown (Informal)
[Building Comparable Corpora for Assessing Multi-Word Term Alignment](https://aclanthology.org/2022.lrec-1.332) (Adjali et al., LREC 2022)
ACL