@inproceedings{prince-chauche-2008-building,
title = "Building a Bilingual Representation of the {R}oget Thesaurus for {F}rench to {E}nglish Machine Translation",
author = "Prince, Violaine and
Chauch{\'e}, Jacques",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/626_paper.pdf",
abstract = "This paper describes a solution to lexical transfer as a trade-off between a dictionary and an ontology. It shows its association to a translation tool based on morpho-syntactical parsing of the source language. It is based on the English Roget Thesaurus and its equivalent, the French Larousse Thesaurus, in a computational framework. Both thesaurii are transformed into vector spaces, and all monolingual entries are represented as vectors, with 1,000 components for English and 873 for French. The indexing concepts of the respective thesaurii are the generation families of the vector spaces. A bilingual data structure transforms French entries into vectors in the English space, by using their equivalencies representations. Word sense disambiguation consists in choosing the appropriate vector among these bilingual vectors, by computing the contextualized vector of a given word in its source sentence, wading it in the English vector space, and computing the closest distance to the different entries in the bilingual data structure beginning with the same source string (i.e. French word). The process has been experimented on a 20,000 words extract of a French novel, Le Petit Prince, and lexical transfer results were found quite encouraging with a recall of 71{\%} and a precision of 86{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="prince-chauche-2008-building">
<titleInfo>
<title>Building a Bilingual Representation of the Roget Thesaurus for French to English Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Violaine</namePart>
<namePart type="family">Prince</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacques</namePart>
<namePart type="family">Chauché</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes a solution to lexical transfer as a trade-off between a dictionary and an ontology. It shows its association to a translation tool based on morpho-syntactical parsing of the source language. It is based on the English Roget Thesaurus and its equivalent, the French Larousse Thesaurus, in a computational framework. Both thesaurii are transformed into vector spaces, and all monolingual entries are represented as vectors, with 1,000 components for English and 873 for French. The indexing concepts of the respective thesaurii are the generation families of the vector spaces. A bilingual data structure transforms French entries into vectors in the English space, by using their equivalencies representations. Word sense disambiguation consists in choosing the appropriate vector among these bilingual vectors, by computing the contextualized vector of a given word in its source sentence, wading it in the English vector space, and computing the closest distance to the different entries in the bilingual data structure beginning with the same source string (i.e. French word). The process has been experimented on a 20,000 words extract of a French novel, Le Petit Prince, and lexical transfer results were found quite encouraging with a recall of 71% and a precision of 86%.</abstract>
<identifier type="citekey">prince-chauche-2008-building</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/626_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a Bilingual Representation of the Roget Thesaurus for French to English Machine Translation
%A Prince, Violaine
%A Chauché, Jacques
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F prince-chauche-2008-building
%X This paper describes a solution to lexical transfer as a trade-off between a dictionary and an ontology. It shows its association to a translation tool based on morpho-syntactical parsing of the source language. It is based on the English Roget Thesaurus and its equivalent, the French Larousse Thesaurus, in a computational framework. Both thesaurii are transformed into vector spaces, and all monolingual entries are represented as vectors, with 1,000 components for English and 873 for French. The indexing concepts of the respective thesaurii are the generation families of the vector spaces. A bilingual data structure transforms French entries into vectors in the English space, by using their equivalencies representations. Word sense disambiguation consists in choosing the appropriate vector among these bilingual vectors, by computing the contextualized vector of a given word in its source sentence, wading it in the English vector space, and computing the closest distance to the different entries in the bilingual data structure beginning with the same source string (i.e. French word). The process has been experimented on a 20,000 words extract of a French novel, Le Petit Prince, and lexical transfer results were found quite encouraging with a recall of 71% and a precision of 86%.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/626_paper.pdf
Markdown (Informal)
[Building a Bilingual Representation of the Roget Thesaurus for French to English Machine Translation](http://www.lrec-conf.org/proceedings/lrec2008/pdf/626_paper.pdf) (Prince & Chauché, LREC 2008)
ACL