@inproceedings{robichaud-cook-2024-wacadie-towards,
title = "{W}a{C}adie: Towards an Acadian {F}rench Corpus",
author = "Robichaud, Jeremy and
Cook, Paul",
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.1514",
pages = "17421--17432",
abstract = "Corpora are important assets within the natural language processing (NLP) and linguistics communities, as they allow the training of models and corpus-based studies of languages. However, corpora do not exist for many languages and language varieties, such as Acadian French. In this paper, we first show that off-the-shelf NLP systems perform more poorly on Acadian French than on standard French. An Acadian French corpus could, therefore, potentially be used to improve NLP models for this dialect. Then, leveraging web-as-corpus methodologies, specifically BootCaT, domain crawling, and social media scraping, we create three corpora of Acadian French. To evaluate these corpora, drawing on the linguistic literature on Acadian French, we propose 22 statistical corpus-based measures of the extent to which a corpus is Acadian French. We use these measures to compare these newly built corpora to known Acadian French text and find that all three corpora include some traces of Acadian French.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="robichaud-cook-2024-wacadie-towards">
<titleInfo>
<title>WaCadie: Towards an Acadian French Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Robichaud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Cook</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>Corpora are important assets within the natural language processing (NLP) and linguistics communities, as they allow the training of models and corpus-based studies of languages. However, corpora do not exist for many languages and language varieties, such as Acadian French. In this paper, we first show that off-the-shelf NLP systems perform more poorly on Acadian French than on standard French. An Acadian French corpus could, therefore, potentially be used to improve NLP models for this dialect. Then, leveraging web-as-corpus methodologies, specifically BootCaT, domain crawling, and social media scraping, we create three corpora of Acadian French. To evaluate these corpora, drawing on the linguistic literature on Acadian French, we propose 22 statistical corpus-based measures of the extent to which a corpus is Acadian French. We use these measures to compare these newly built corpora to known Acadian French text and find that all three corpora include some traces of Acadian French.</abstract>
<identifier type="citekey">robichaud-cook-2024-wacadie-towards</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1514</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>17421</start>
<end>17432</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WaCadie: Towards an Acadian French Corpus
%A Robichaud, Jeremy
%A Cook, Paul
%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 robichaud-cook-2024-wacadie-towards
%X Corpora are important assets within the natural language processing (NLP) and linguistics communities, as they allow the training of models and corpus-based studies of languages. However, corpora do not exist for many languages and language varieties, such as Acadian French. In this paper, we first show that off-the-shelf NLP systems perform more poorly on Acadian French than on standard French. An Acadian French corpus could, therefore, potentially be used to improve NLP models for this dialect. Then, leveraging web-as-corpus methodologies, specifically BootCaT, domain crawling, and social media scraping, we create three corpora of Acadian French. To evaluate these corpora, drawing on the linguistic literature on Acadian French, we propose 22 statistical corpus-based measures of the extent to which a corpus is Acadian French. We use these measures to compare these newly built corpora to known Acadian French text and find that all three corpora include some traces of Acadian French.
%U https://aclanthology.org/2024.lrec-main.1514
%P 17421-17432
Markdown (Informal)
[WaCadie: Towards an Acadian French Corpus](https://aclanthology.org/2024.lrec-main.1514) (Robichaud & Cook, LREC-COLING 2024)
ACL
- Jeremy Robichaud and Paul Cook. 2024. WaCadie: Towards an Acadian French Corpus. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 17421–17432, Torino, Italia. ELRA and ICCL.