@inproceedings{priya-etal-2026-pos,
title = "{POS} Tagging in Low-Resource {M}aithili Language: Specific Challenges and Nuances",
author = "Priya, Shivani and
Jha, Shruti and
Jha, Urmila and
Jha, Girish Nath and
Tiwari, Deepali and
Raj, Jyoti",
editor = "Jha, Girish Nath and
Bali, Kalika and
L, Sobha and
Kumar, Devendr",
booktitle = "Proceedings of the 8th Workshop on {I}ndian Language Data: Resources and Evaluation",
month = may,
year = "2026",
address = "Palma, Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.wildre-1.9/",
doi = "10.63317/27ugx7nj4vvs",
pages = "67--74",
abstract = "Abstract Part-of-Speech (POS) tagging is a key step in Natural Language Processing (NLP), laying the groundwork for more advanced syntactic and semantic tasks. Despite Maithili{'}s status as an Indo-Aryan language with a rich literary tradition and official recognition in India, computational resources for it are still very limited. In this paper, the creation of an annotated corpus of 25,000 sentences drawn from the fields of health, tourism, and administration is described with the hierarchical tagset currently used for Maithili. This paper also indicates that standard tagsets, typically adapted from English or Hindi, fail to capture the linguistic nuances of Maithili. This underestimates the need for a dedicated tagging framework that considers characteristics like vocative particles, verbal nuances, honorific complexities. Keywords: Parts of Speech, Natural Language Processing, Maithili, annotation"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="priya-etal-2026-pos">
<titleInfo>
<title>POS Tagging in Low-Resource Maithili Language: Specific Challenges and Nuances</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shivani</namePart>
<namePart type="family">Priya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Jha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Urmila</namePart>
<namePart type="family">Jha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Girish</namePart>
<namePart type="given">Nath</namePart>
<namePart type="family">Jha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deepali</namePart>
<namePart type="family">Tiwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jyoti</namePart>
<namePart type="family">Raj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Indian Language Data: Resources and Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Girish</namePart>
<namePart type="given">Nath</namePart>
<namePart type="family">Jha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="family">L</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Devendr</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Abstract Part-of-Speech (POS) tagging is a key step in Natural Language Processing (NLP), laying the groundwork for more advanced syntactic and semantic tasks. Despite Maithili’s status as an Indo-Aryan language with a rich literary tradition and official recognition in India, computational resources for it are still very limited. In this paper, the creation of an annotated corpus of 25,000 sentences drawn from the fields of health, tourism, and administration is described with the hierarchical tagset currently used for Maithili. This paper also indicates that standard tagsets, typically adapted from English or Hindi, fail to capture the linguistic nuances of Maithili. This underestimates the need for a dedicated tagging framework that considers characteristics like vocative particles, verbal nuances, honorific complexities. Keywords: Parts of Speech, Natural Language Processing, Maithili, annotation</abstract>
<identifier type="citekey">priya-etal-2026-pos</identifier>
<identifier type="doi">10.63317/27ugx7nj4vvs</identifier>
<location>
<url>https://aclanthology.org/2026.wildre-1.9/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>67</start>
<end>74</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T POS Tagging in Low-Resource Maithili Language: Specific Challenges and Nuances
%A Priya, Shivani
%A Jha, Shruti
%A Jha, Urmila
%A Jha, Girish Nath
%A Tiwari, Deepali
%A Raj, Jyoti
%Y Jha, Girish Nath
%Y Bali, Kalika
%Y L, Sobha
%Y Kumar, Devendr
%S Proceedings of the 8th Workshop on Indian Language Data: Resources and Evaluation
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca, Spain
%F priya-etal-2026-pos
%X Abstract Part-of-Speech (POS) tagging is a key step in Natural Language Processing (NLP), laying the groundwork for more advanced syntactic and semantic tasks. Despite Maithili’s status as an Indo-Aryan language with a rich literary tradition and official recognition in India, computational resources for it are still very limited. In this paper, the creation of an annotated corpus of 25,000 sentences drawn from the fields of health, tourism, and administration is described with the hierarchical tagset currently used for Maithili. This paper also indicates that standard tagsets, typically adapted from English or Hindi, fail to capture the linguistic nuances of Maithili. This underestimates the need for a dedicated tagging framework that considers characteristics like vocative particles, verbal nuances, honorific complexities. Keywords: Parts of Speech, Natural Language Processing, Maithili, annotation
%R 10.63317/27ugx7nj4vvs
%U https://aclanthology.org/2026.wildre-1.9/
%U https://doi.org/10.63317/27ugx7nj4vvs
%P 67-74
Markdown (Informal)
[POS Tagging in Low-Resource Maithili Language: Specific Challenges and Nuances](https://aclanthology.org/2026.wildre-1.9/) (Priya et al., WILDRE 2026)
ACL