@inproceedings{angleraud-etal-2025-annotating,
title = "Annotating the {F}rench {W}iktionary with supersenses for large scale lexical analysis: a use case to assess form-meaning relationships within the nominal lexicon",
author = "Angleraud, Nicolas and
Barque, Lucie and
Candito, Marie",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.356/",
pages = "5321--5332",
abstract = "Many languages lack broad-coverage, semantically annotated lexical resources, which limits empirical research on lexical semantics for these languages. In this paper, we report on how we automatically enriched the French Wiktionnary with general semantic classes, known as supersenses, using a limited amount of manually annotated data. We trained a classifier combining sense definition classification and sense exemplars classification. The resulting resource, with an evaluated supersense accuracy of nearly 85{\%} (92{\%} for hypersenses), is used in a case study illustrating how such an semantically enriched resource can be leveraged to empirically test linguistic hypotheses about the lexicon, on a large scale."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="angleraud-etal-2025-annotating">
<titleInfo>
<title>Annotating the French Wiktionary with supersenses for large scale lexical analysis: a use case to assess form-meaning relationships within the nominal lexicon</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Angleraud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Barque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Candito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many languages lack broad-coverage, semantically annotated lexical resources, which limits empirical research on lexical semantics for these languages. In this paper, we report on how we automatically enriched the French Wiktionnary with general semantic classes, known as supersenses, using a limited amount of manually annotated data. We trained a classifier combining sense definition classification and sense exemplars classification. The resulting resource, with an evaluated supersense accuracy of nearly 85% (92% for hypersenses), is used in a case study illustrating how such an semantically enriched resource can be leveraged to empirically test linguistic hypotheses about the lexicon, on a large scale.</abstract>
<identifier type="citekey">angleraud-etal-2025-annotating</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.356/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>5321</start>
<end>5332</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Annotating the French Wiktionary with supersenses for large scale lexical analysis: a use case to assess form-meaning relationships within the nominal lexicon
%A Angleraud, Nicolas
%A Barque, Lucie
%A Candito, Marie
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F angleraud-etal-2025-annotating
%X Many languages lack broad-coverage, semantically annotated lexical resources, which limits empirical research on lexical semantics for these languages. In this paper, we report on how we automatically enriched the French Wiktionnary with general semantic classes, known as supersenses, using a limited amount of manually annotated data. We trained a classifier combining sense definition classification and sense exemplars classification. The resulting resource, with an evaluated supersense accuracy of nearly 85% (92% for hypersenses), is used in a case study illustrating how such an semantically enriched resource can be leveraged to empirically test linguistic hypotheses about the lexicon, on a large scale.
%U https://aclanthology.org/2025.coling-main.356/
%P 5321-5332
Markdown (Informal)
[Annotating the French Wiktionary with supersenses for large scale lexical analysis: a use case to assess form-meaning relationships within the nominal lexicon](https://aclanthology.org/2025.coling-main.356/) (Angleraud et al., COLING 2025)
ACL