@inproceedings{millour-etal-2024-agettivu-aggitivu,
title = "Agettivu, Aggitivu o Aghjettivu? {POS} Tagging {C}orsican Dialects",
author = "Millour, Alice and
Brasile, Lorenza and
Ghia, Alberto and
Kevers, Laurent",
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.52",
pages = "600--608",
abstract = "In this paper we present a series of experiments towards POS tagging Corsican, a less-resourced language spoken in Corsica and linguistically related to Italian. The first contribution is Corsican-POS, the first gold standard POS-tagged corpus for Corsica, composed of 500 sentences manually annotated with the Universal POS tagset. Our second contribution is a set of experiments and evaluation of POS tagging models which starts with a baseline model for Italian and is aimed at finding the best training configuration, namely in terms of the size and combination strategy of the existing raw and annotated resources. These experiments result in (i) the first POS tagger for Corsican, reaching an accuracy of 93.38{\%}, (ii) a quantification of the gain provided by the use of each available resource. We find that the optimal configuration uses Italian word embeddings further specialized with Corsican embeddings and trained on the largest gold corpus for Corsican available so far.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="millour-etal-2024-agettivu-aggitivu">
<titleInfo>
<title>Agettivu, Aggitivu o Aghjettivu? POS Tagging Corsican Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Millour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lorenza</namePart>
<namePart type="family">Brasile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Ghia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Kevers</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>In this paper we present a series of experiments towards POS tagging Corsican, a less-resourced language spoken in Corsica and linguistically related to Italian. The first contribution is Corsican-POS, the first gold standard POS-tagged corpus for Corsica, composed of 500 sentences manually annotated with the Universal POS tagset. Our second contribution is a set of experiments and evaluation of POS tagging models which starts with a baseline model for Italian and is aimed at finding the best training configuration, namely in terms of the size and combination strategy of the existing raw and annotated resources. These experiments result in (i) the first POS tagger for Corsican, reaching an accuracy of 93.38%, (ii) a quantification of the gain provided by the use of each available resource. We find that the optimal configuration uses Italian word embeddings further specialized with Corsican embeddings and trained on the largest gold corpus for Corsican available so far.</abstract>
<identifier type="citekey">millour-etal-2024-agettivu-aggitivu</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.52</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>600</start>
<end>608</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Agettivu, Aggitivu o Aghjettivu? POS Tagging Corsican Dialects
%A Millour, Alice
%A Brasile, Lorenza
%A Ghia, Alberto
%A Kevers, Laurent
%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 millour-etal-2024-agettivu-aggitivu
%X In this paper we present a series of experiments towards POS tagging Corsican, a less-resourced language spoken in Corsica and linguistically related to Italian. The first contribution is Corsican-POS, the first gold standard POS-tagged corpus for Corsica, composed of 500 sentences manually annotated with the Universal POS tagset. Our second contribution is a set of experiments and evaluation of POS tagging models which starts with a baseline model for Italian and is aimed at finding the best training configuration, namely in terms of the size and combination strategy of the existing raw and annotated resources. These experiments result in (i) the first POS tagger for Corsican, reaching an accuracy of 93.38%, (ii) a quantification of the gain provided by the use of each available resource. We find that the optimal configuration uses Italian word embeddings further specialized with Corsican embeddings and trained on the largest gold corpus for Corsican available so far.
%U https://aclanthology.org/2024.lrec-main.52
%P 600-608
Markdown (Informal)
[Agettivu, Aggitivu o Aghjettivu? POS Tagging Corsican Dialects](https://aclanthology.org/2024.lrec-main.52) (Millour et al., LREC-COLING 2024)
ACL
- Alice Millour, Lorenza Brasile, Alberto Ghia, and Laurent Kevers. 2024. Agettivu, Aggitivu o Aghjettivu? POS Tagging Corsican Dialects. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 600–608, Torino, Italia. ELRA and ICCL.