@inproceedings{de-jesus-nunes-2024-data-collection,
title = "Data Collection Pipeline for Low-Resource Languages: A Case Study on Constructing a Tetun Text Corpus",
author = "de Jesus, Gabriel and
Nunes, S{\'e}rgio Sobral",
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.390",
pages = "4368--4380",
abstract = "This paper proposes Labadain Crawler, a data collection pipeline tailored to automate and optimize the process of constructing textual corpora from the web, with a specific target to low-resource languages. The system is built on top of Nutch, an open-source web crawler and data extraction framework, and incorporates language processing components such as a tokenizer and a language identification model. The pipeline efficacy is demonstrated through successful testing with Tetun, one of Timor-Leste{'}s official languages, resulting in the construction of a high-quality Tetun text corpus comprising 321.7k sentences extracted from over 22k web pages. The contributions of this paper include the development of a Tetun tokenizer, a Tetun language identification model, and a Tetun text corpus, marking an important milestone in Tetun text information retrieval.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-jesus-nunes-2024-data-collection">
<titleInfo>
<title>Data Collection Pipeline for Low-Resource Languages: A Case Study on Constructing a Tetun Text Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">de Jesus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sérgio</namePart>
<namePart type="given">Sobral</namePart>
<namePart type="family">Nunes</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 proposes Labadain Crawler, a data collection pipeline tailored to automate and optimize the process of constructing textual corpora from the web, with a specific target to low-resource languages. The system is built on top of Nutch, an open-source web crawler and data extraction framework, and incorporates language processing components such as a tokenizer and a language identification model. The pipeline efficacy is demonstrated through successful testing with Tetun, one of Timor-Leste’s official languages, resulting in the construction of a high-quality Tetun text corpus comprising 321.7k sentences extracted from over 22k web pages. The contributions of this paper include the development of a Tetun tokenizer, a Tetun language identification model, and a Tetun text corpus, marking an important milestone in Tetun text information retrieval.</abstract>
<identifier type="citekey">de-jesus-nunes-2024-data-collection</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.390</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4368</start>
<end>4380</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Collection Pipeline for Low-Resource Languages: A Case Study on Constructing a Tetun Text Corpus
%A de Jesus, Gabriel
%A Nunes, Sérgio Sobral
%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 de-jesus-nunes-2024-data-collection
%X This paper proposes Labadain Crawler, a data collection pipeline tailored to automate and optimize the process of constructing textual corpora from the web, with a specific target to low-resource languages. The system is built on top of Nutch, an open-source web crawler and data extraction framework, and incorporates language processing components such as a tokenizer and a language identification model. The pipeline efficacy is demonstrated through successful testing with Tetun, one of Timor-Leste’s official languages, resulting in the construction of a high-quality Tetun text corpus comprising 321.7k sentences extracted from over 22k web pages. The contributions of this paper include the development of a Tetun tokenizer, a Tetun language identification model, and a Tetun text corpus, marking an important milestone in Tetun text information retrieval.
%U https://aclanthology.org/2024.lrec-main.390
%P 4368-4380
Markdown (Informal)
[Data Collection Pipeline for Low-Resource Languages: A Case Study on Constructing a Tetun Text Corpus](https://aclanthology.org/2024.lrec-main.390) (de Jesus & Nunes, LREC-COLING 2024)
ACL