@inproceedings{cardon-grabar-2020-french-corpus,
title = "A {F}rench Corpus for Semantic Similarity",
author = "Cardon, R{\'e}mi and
Grabar, Natalia",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.851",
pages = "6889--6894",
abstract = "Semantic similarity is an area of Natural Language Processing that is useful for several downstream applications, such as machine translation, natural language generation, information retrieval, or question answering. The task consists in assessing the extent to which two sentences express or do not express the same meaning. To do so, corpora with graded pairs of sentences are required. The grade is positioned on a given scale, usually going from 0 (completely unrelated) to 5 (equivalent semantics). In this work, we introduce such a corpus for French, the first that we know of. It is comprised of 1,010 sentence pairs with grades from five annotators. We describe the annotation process, analyse these data, and perform a few experiments for the automatic grading of semantic similarity.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cardon-grabar-2020-french-corpus">
<titleInfo>
<title>A French Corpus for Semantic Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rémi</namePart>
<namePart type="family">Cardon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Grabar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Semantic similarity is an area of Natural Language Processing that is useful for several downstream applications, such as machine translation, natural language generation, information retrieval, or question answering. The task consists in assessing the extent to which two sentences express or do not express the same meaning. To do so, corpora with graded pairs of sentences are required. The grade is positioned on a given scale, usually going from 0 (completely unrelated) to 5 (equivalent semantics). In this work, we introduce such a corpus for French, the first that we know of. It is comprised of 1,010 sentence pairs with grades from five annotators. We describe the annotation process, analyse these data, and perform a few experiments for the automatic grading of semantic similarity.</abstract>
<identifier type="citekey">cardon-grabar-2020-french-corpus</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.851</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6889</start>
<end>6894</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A French Corpus for Semantic Similarity
%A Cardon, Rémi
%A Grabar, Natalia
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F cardon-grabar-2020-french-corpus
%X Semantic similarity is an area of Natural Language Processing that is useful for several downstream applications, such as machine translation, natural language generation, information retrieval, or question answering. The task consists in assessing the extent to which two sentences express or do not express the same meaning. To do so, corpora with graded pairs of sentences are required. The grade is positioned on a given scale, usually going from 0 (completely unrelated) to 5 (equivalent semantics). In this work, we introduce such a corpus for French, the first that we know of. It is comprised of 1,010 sentence pairs with grades from five annotators. We describe the annotation process, analyse these data, and perform a few experiments for the automatic grading of semantic similarity.
%U https://aclanthology.org/2020.lrec-1.851
%P 6889-6894
Markdown (Informal)
[A French Corpus for Semantic Similarity](https://aclanthology.org/2020.lrec-1.851) (Cardon & Grabar, LREC 2020)
ACL
- Rémi Cardon and Natalia Grabar. 2020. A French Corpus for Semantic Similarity. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 6889–6894, Marseille, France. European Language Resources Association.