@inproceedings{garcia-holgado-vergez-couret-2024-empowering-low,
title = "Empowering Low-Resource Regional Languages with Lexicons : A Comparative Study of {NLP} Tools for Morphosyntactic Analysis",
author = "Garcia Holgado, Cristina and
Vergez-Couret, Marianne",
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.510",
pages = "5747--5756",
abstract = "We investigate the effect of integrating lexicon information to an extremely low-resource language when annotated data is scarce for morpho-syntactic analysis. Obtaining such data and linguistic resources for these languages are usually constrained by a lack of human and financial resources making this task particularly challenging. In this paper, we describe the collection and leverage of a bilingual lexicon for Poitevin-Saintongeais, a regional language of France, to create augmented data through a neighbor-based distributional method. We assess this lexicon-driven approach in improving POS tagging while using different lexicon and augmented data sizes. To evaluate this strategy, we compare two distinct paradigms: neural networks, which typically require extensive data, and a conventional probabilistic approach, in which a lexicon is instrumental in its performance. Our findings reveal that the lexicon is a valuable asset for all models, but in particular for neural, demonstrating an enhanced generalization across diverse classes without requiring an extensive lexicon size.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-holgado-vergez-couret-2024-empowering-low">
<titleInfo>
<title>Empowering Low-Resource Regional Languages with Lexicons : A Comparative Study of NLP Tools for Morphosyntactic Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Garcia Holgado</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianne</namePart>
<namePart type="family">Vergez-Couret</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>We investigate the effect of integrating lexicon information to an extremely low-resource language when annotated data is scarce for morpho-syntactic analysis. Obtaining such data and linguistic resources for these languages are usually constrained by a lack of human and financial resources making this task particularly challenging. In this paper, we describe the collection and leverage of a bilingual lexicon for Poitevin-Saintongeais, a regional language of France, to create augmented data through a neighbor-based distributional method. We assess this lexicon-driven approach in improving POS tagging while using different lexicon and augmented data sizes. To evaluate this strategy, we compare two distinct paradigms: neural networks, which typically require extensive data, and a conventional probabilistic approach, in which a lexicon is instrumental in its performance. Our findings reveal that the lexicon is a valuable asset for all models, but in particular for neural, demonstrating an enhanced generalization across diverse classes without requiring an extensive lexicon size.</abstract>
<identifier type="citekey">garcia-holgado-vergez-couret-2024-empowering-low</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.510</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>5747</start>
<end>5756</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Empowering Low-Resource Regional Languages with Lexicons : A Comparative Study of NLP Tools for Morphosyntactic Analysis
%A Garcia Holgado, Cristina
%A Vergez-Couret, Marianne
%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 garcia-holgado-vergez-couret-2024-empowering-low
%X We investigate the effect of integrating lexicon information to an extremely low-resource language when annotated data is scarce for morpho-syntactic analysis. Obtaining such data and linguistic resources for these languages are usually constrained by a lack of human and financial resources making this task particularly challenging. In this paper, we describe the collection and leverage of a bilingual lexicon for Poitevin-Saintongeais, a regional language of France, to create augmented data through a neighbor-based distributional method. We assess this lexicon-driven approach in improving POS tagging while using different lexicon and augmented data sizes. To evaluate this strategy, we compare two distinct paradigms: neural networks, which typically require extensive data, and a conventional probabilistic approach, in which a lexicon is instrumental in its performance. Our findings reveal that the lexicon is a valuable asset for all models, but in particular for neural, demonstrating an enhanced generalization across diverse classes without requiring an extensive lexicon size.
%U https://aclanthology.org/2024.lrec-main.510
%P 5747-5756
Markdown (Informal)
[Empowering Low-Resource Regional Languages with Lexicons : A Comparative Study of NLP Tools for Morphosyntactic Analysis](https://aclanthology.org/2024.lrec-main.510) (Garcia Holgado & Vergez-Couret, LREC-COLING 2024)
ACL