@inproceedings{viksna-skadina-2024-multileg-dataset,
title = "{M}ulti{L}eg: Dataset for Text Sanitisation in Less-resourced Languages",
author = "V{\=\i}ksna, Rinalds and
Skadi{\c{n}}a, Inguna",
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.1028",
pages = "11776--11782",
abstract = "Text sanitization is the task of detecting and removing personal information from the text. While it has been well-studied in monolingual settings, today, there is also a need for multilingual text sanitization. In this paper, we introduce MultiLeg: a parallel, multilingual named entity (NE) dataset consisting of documents from the Court of Justice of the European Union annotated with semantic categories suitable for text sanitization. The dataset is available in 8 languages, and it contains 3082 parallel text segments for each language. We also show that the pseudonymized dataset remains useful for downstream tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="viksna-skadina-2024-multileg-dataset">
<titleInfo>
<title>MultiLeg: Dataset for Text Sanitisation in Less-resourced Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rinalds</namePart>
<namePart type="family">Vīksna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inguna</namePart>
<namePart type="family">Skadiņa</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>Text sanitization is the task of detecting and removing personal information from the text. While it has been well-studied in monolingual settings, today, there is also a need for multilingual text sanitization. In this paper, we introduce MultiLeg: a parallel, multilingual named entity (NE) dataset consisting of documents from the Court of Justice of the European Union annotated with semantic categories suitable for text sanitization. The dataset is available in 8 languages, and it contains 3082 parallel text segments for each language. We also show that the pseudonymized dataset remains useful for downstream tasks.</abstract>
<identifier type="citekey">viksna-skadina-2024-multileg-dataset</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1028</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11776</start>
<end>11782</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MultiLeg: Dataset for Text Sanitisation in Less-resourced Languages
%A Vīksna, Rinalds
%A Skadiņa, Inguna
%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 viksna-skadina-2024-multileg-dataset
%X Text sanitization is the task of detecting and removing personal information from the text. While it has been well-studied in monolingual settings, today, there is also a need for multilingual text sanitization. In this paper, we introduce MultiLeg: a parallel, multilingual named entity (NE) dataset consisting of documents from the Court of Justice of the European Union annotated with semantic categories suitable for text sanitization. The dataset is available in 8 languages, and it contains 3082 parallel text segments for each language. We also show that the pseudonymized dataset remains useful for downstream tasks.
%U https://aclanthology.org/2024.lrec-main.1028
%P 11776-11782
Markdown (Informal)
[MultiLeg: Dataset for Text Sanitisation in Less-resourced Languages](https://aclanthology.org/2024.lrec-main.1028) (Vīksna & Skadiņa, LREC-COLING 2024)
ACL