@inproceedings{vergez-couret-etal-2024-lofloc,
title = "Lofl{\`o}c: A Morphological Lexicon for {O}ccitan using {U}niversal {D}ependencies",
author = "Vergez-Couret, Marianne and
Bras, Myriam and
Mileti{\'c}, Aleksandra and
Poujade, Clamen{\c{c}}a",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.937",
pages = "10716--10724",
abstract = "This paper presents Lofl{\`o}c (Lexic ob{\`e}rt flechit Occitan {--} Open Inflected Lexicon of Occitan), a morphological lexicon for Occitan. Even though the lexicon no longer occupies the same place in the NLP pipeline since the advent of large language models, it remains a crucial resource for low-resourced languages. Occitan is a Romance language spoken in the south of France and in parts of Italy and Spain. It is not recognized as an official language in France and no standard variety is shared across the area. To the best of our knowledge, Lofl{\`o}c is the first publicly available lexicon for Occitan. It contains 650 thousand entries for 57 thousand lemmas. Each entry is accompanied by the corresponding Universal Dependencies Part-of-Speech tag. We show that the lexicon has solid coverage on the existing freely available corpora of Occitan in four major dialects. Coverage gaps on multi-dialect corpora are overwhelmingly driven by dialectal variation, which affects both open and closed classes. Based on this analysis we propose directions for future improvements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vergez-couret-etal-2024-lofloc">
<titleInfo>
<title>Loflòc: A Morphological Lexicon for Occitan using Universal Dependencies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marianne</namePart>
<namePart type="family">Vergez-Couret</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Myriam</namePart>
<namePart type="family">Bras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandra</namePart>
<namePart type="family">Miletić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clamença</namePart>
<namePart type="family">Poujade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents Loflòc (Lexic obèrt flechit Occitan – Open Inflected Lexicon of Occitan), a morphological lexicon for Occitan. Even though the lexicon no longer occupies the same place in the NLP pipeline since the advent of large language models, it remains a crucial resource for low-resourced languages. Occitan is a Romance language spoken in the south of France and in parts of Italy and Spain. It is not recognized as an official language in France and no standard variety is shared across the area. To the best of our knowledge, Loflòc is the first publicly available lexicon for Occitan. It contains 650 thousand entries for 57 thousand lemmas. Each entry is accompanied by the corresponding Universal Dependencies Part-of-Speech tag. We show that the lexicon has solid coverage on the existing freely available corpora of Occitan in four major dialects. Coverage gaps on multi-dialect corpora are overwhelmingly driven by dialectal variation, which affects both open and closed classes. Based on this analysis we propose directions for future improvements.</abstract>
<identifier type="citekey">vergez-couret-etal-2024-lofloc</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.937</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>10716</start>
<end>10724</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Loflòc: A Morphological Lexicon for Occitan using Universal Dependencies
%A Vergez-Couret, Marianne
%A Bras, Myriam
%A Miletić, Aleksandra
%A Poujade, Clamença
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F vergez-couret-etal-2024-lofloc
%X This paper presents Loflòc (Lexic obèrt flechit Occitan – Open Inflected Lexicon of Occitan), a morphological lexicon for Occitan. Even though the lexicon no longer occupies the same place in the NLP pipeline since the advent of large language models, it remains a crucial resource for low-resourced languages. Occitan is a Romance language spoken in the south of France and in parts of Italy and Spain. It is not recognized as an official language in France and no standard variety is shared across the area. To the best of our knowledge, Loflòc is the first publicly available lexicon for Occitan. It contains 650 thousand entries for 57 thousand lemmas. Each entry is accompanied by the corresponding Universal Dependencies Part-of-Speech tag. We show that the lexicon has solid coverage on the existing freely available corpora of Occitan in four major dialects. Coverage gaps on multi-dialect corpora are overwhelmingly driven by dialectal variation, which affects both open and closed classes. Based on this analysis we propose directions for future improvements.
%U https://aclanthology.org/2024.lrec-main.937
%P 10716-10724
Markdown (Informal)
[Loflòc: A Morphological Lexicon for Occitan using Universal Dependencies](https://aclanthology.org/2024.lrec-main.937) (Vergez-Couret et al., LREC-COLING 2024)
ACL