@inproceedings{kumar-etal-2024-part,
title = "Part-of-speech Tagging for Extremely Low-resource {I}ndian Languages",
author = "Kumar, Sanjeev and
Jyothi, Preethi and
Bhattacharyya, Pushpak",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.857/",
doi = "10.18653/v1/2024.findings-acl.857",
pages = "14422--14431",
abstract = "Modern natural language processing (NLP) systems thrive when given access to large datasets. However, a large fraction of the world`s languages are not privy to such benefits due to sparse documentation and inadequate digital representation. This is especially true for Indian regional languages. As a first step towards expanding the reach of NLP technologies to extremely low-resource Indian languages, we present a new parallel part-of-speech (POS) evaluation dataset for Angika, Magahi, Bhojpuri and Hindi. Angika, Magahi, Bhojpuri, along with the more well-known Hindi, are all languages spoken in the Indian states of Bihar, Jharkhand and West Bengal. Ours is notably the first NLP resource, even for a shallow NLP task like POS-tagging, for Angika. We establish POS-tagging baselines using state-of-the-art multilingual pretrained language models (PLMs) finetuned on Hindi data, and show zero-shot evaluations on the other three languages. While all four languages use the same Devanagari script, pretrained tokenizers underperform in zero-shot on the three languages. We propose a simple look-back fix to address the tokenization challenge yielding F1-score improvements of up to 8{\%} on Angika and show how it comes very close to an oracle setting when the underlying Hindi word is known (and can be accurately tokenized)."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2024-part">
<titleInfo>
<title>Part-of-speech Tagging for Extremely Low-resource Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanjeev</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preethi</namePart>
<namePart type="family">Jyothi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Modern natural language processing (NLP) systems thrive when given access to large datasets. However, a large fraction of the world‘s languages are not privy to such benefits due to sparse documentation and inadequate digital representation. This is especially true for Indian regional languages. As a first step towards expanding the reach of NLP technologies to extremely low-resource Indian languages, we present a new parallel part-of-speech (POS) evaluation dataset for Angika, Magahi, Bhojpuri and Hindi. Angika, Magahi, Bhojpuri, along with the more well-known Hindi, are all languages spoken in the Indian states of Bihar, Jharkhand and West Bengal. Ours is notably the first NLP resource, even for a shallow NLP task like POS-tagging, for Angika. We establish POS-tagging baselines using state-of-the-art multilingual pretrained language models (PLMs) finetuned on Hindi data, and show zero-shot evaluations on the other three languages. While all four languages use the same Devanagari script, pretrained tokenizers underperform in zero-shot on the three languages. We propose a simple look-back fix to address the tokenization challenge yielding F1-score improvements of up to 8% on Angika and show how it comes very close to an oracle setting when the underlying Hindi word is known (and can be accurately tokenized).</abstract>
<identifier type="citekey">kumar-etal-2024-part</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.857</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.857/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>14422</start>
<end>14431</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Part-of-speech Tagging for Extremely Low-resource Indian Languages
%A Kumar, Sanjeev
%A Jyothi, Preethi
%A Bhattacharyya, Pushpak
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F kumar-etal-2024-part
%X Modern natural language processing (NLP) systems thrive when given access to large datasets. However, a large fraction of the world‘s languages are not privy to such benefits due to sparse documentation and inadequate digital representation. This is especially true for Indian regional languages. As a first step towards expanding the reach of NLP technologies to extremely low-resource Indian languages, we present a new parallel part-of-speech (POS) evaluation dataset for Angika, Magahi, Bhojpuri and Hindi. Angika, Magahi, Bhojpuri, along with the more well-known Hindi, are all languages spoken in the Indian states of Bihar, Jharkhand and West Bengal. Ours is notably the first NLP resource, even for a shallow NLP task like POS-tagging, for Angika. We establish POS-tagging baselines using state-of-the-art multilingual pretrained language models (PLMs) finetuned on Hindi data, and show zero-shot evaluations on the other three languages. While all four languages use the same Devanagari script, pretrained tokenizers underperform in zero-shot on the three languages. We propose a simple look-back fix to address the tokenization challenge yielding F1-score improvements of up to 8% on Angika and show how it comes very close to an oracle setting when the underlying Hindi word is known (and can be accurately tokenized).
%R 10.18653/v1/2024.findings-acl.857
%U https://aclanthology.org/2024.findings-acl.857/
%U https://doi.org/10.18653/v1/2024.findings-acl.857
%P 14422-14431
Markdown (Informal)
[Part-of-speech Tagging for Extremely Low-resource Indian Languages](https://aclanthology.org/2024.findings-acl.857/) (Kumar et al., Findings 2024)
ACL