@inproceedings{dolinska-bernhard-2024-pos,
title = "{POS} Tagging for the Endangered Dagur Language",
author = "Doli{\'n}ska, Joanna and
Bernhard, Delphine",
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.1130/",
pages = "12906--12916",
abstract = "The application of natural language processing tools opens new ways for the documentation and revitalization of under-resourced languages. In this article we aim to investigate the feasibility of automatic part-of-speech (POS) tagging for Dagur, which is an endangered Mongolic language spoken mainly in northeast China, with no official written standard for all Dagur dialects. We present a new manually annotated corpus for Dagur, which includes about 1,200 tokens, and detail the decisions made during the annotation process. This corpus is used to test transfer of models from other languages, especially from Buryat, which is currently the only Mongolic language included in the Universal Dependencies corpora. We applied the models trained by de Vries et al. (2022) to the Dagur corpus and continued training these models on Buryat. We analyse the results with respect to language families, script and POS distribution, in three different zero-shot settings: (1) unrelated, (2) related and (3) unrelated+related language."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dolinska-bernhard-2024-pos">
<titleInfo>
<title>POS Tagging for the Endangered Dagur Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Dolińska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Delphine</namePart>
<namePart type="family">Bernhard</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>The application of natural language processing tools opens new ways for the documentation and revitalization of under-resourced languages. In this article we aim to investigate the feasibility of automatic part-of-speech (POS) tagging for Dagur, which is an endangered Mongolic language spoken mainly in northeast China, with no official written standard for all Dagur dialects. We present a new manually annotated corpus for Dagur, which includes about 1,200 tokens, and detail the decisions made during the annotation process. This corpus is used to test transfer of models from other languages, especially from Buryat, which is currently the only Mongolic language included in the Universal Dependencies corpora. We applied the models trained by de Vries et al. (2022) to the Dagur corpus and continued training these models on Buryat. We analyse the results with respect to language families, script and POS distribution, in three different zero-shot settings: (1) unrelated, (2) related and (3) unrelated+related language.</abstract>
<identifier type="citekey">dolinska-bernhard-2024-pos</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1130/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12906</start>
<end>12916</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T POS Tagging for the Endangered Dagur Language
%A Dolińska, Joanna
%A Bernhard, Delphine
%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 dolinska-bernhard-2024-pos
%X The application of natural language processing tools opens new ways for the documentation and revitalization of under-resourced languages. In this article we aim to investigate the feasibility of automatic part-of-speech (POS) tagging for Dagur, which is an endangered Mongolic language spoken mainly in northeast China, with no official written standard for all Dagur dialects. We present a new manually annotated corpus for Dagur, which includes about 1,200 tokens, and detail the decisions made during the annotation process. This corpus is used to test transfer of models from other languages, especially from Buryat, which is currently the only Mongolic language included in the Universal Dependencies corpora. We applied the models trained by de Vries et al. (2022) to the Dagur corpus and continued training these models on Buryat. We analyse the results with respect to language families, script and POS distribution, in three different zero-shot settings: (1) unrelated, (2) related and (3) unrelated+related language.
%U https://aclanthology.org/2024.lrec-main.1130/
%P 12906-12916
Markdown (Informal)
[POS Tagging for the Endangered Dagur Language](https://aclanthology.org/2024.lrec-main.1130/) (Dolińska & Bernhard, LREC-COLING 2024)
ACL
- Joanna Dolińska and Delphine Bernhard. 2024. POS Tagging for the Endangered Dagur Language. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 12906–12916, Torino, Italia. ELRA and ICCL.