@inproceedings{dhamala-etal-2026-evaluating,
title = "Evaluating {N}epali {NER} and {POS} Tagging Models on the Achhami Dialect",
author = "Dhamala, Samikshya and
Beejukchhen, Rishav and
Thakulla, Subresh and
Kadayat, Bikash and
Khadka, Supriya",
editor = "Ojha, Atul Kr. and
Sakti, Sakriani and
Soria, Claudia and
Melero, Maite and
McCrae, John P. and
Lignos, Constantine and
Liu, Chao-Hong and
Claramunt, German Rigau and
Rehm, Georg",
booktitle = "Proceedings of the {SIGUL} 2026 Joint Workshop with {ELE}, {EURALI}, and {DCLRL}: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages",
month = may,
year = "2026",
address = "Palma, Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.sigul-1.21/",
doi = "10.63317/5hmcq734e4yd",
pages = "210--221",
abstract = "Nepali Natural Language Processing (NLP) models are typically trained and evaluated on Standard Nepali, which can introduce bias against regional dialects. This study investigates the performance of Named Entity Recognition (NER) and Part-of-Speech (POS) tagging models on Achhami, a Far-Western dialect of Nepal. A parallel corpus of 300 sentence pairs was created, covering news, cultural topics, and everyday conversations. Achhami translations were produced by native speakers to preserve linguistic authenticity. The evaluation compared fine-tuned Transformer models with large language models using zero-shot prompting. Across both tasks, all models showed consistent performance degradation on the Achhami dialect. For NER, F1 scores decreased by 2.12 to 3.97 percent. Claude 3.5 Haiku achieved the best NER performance, while the monolingual NepBertA model unexpectedly outperformed multilingual alternatives, challenging assumptions about multilingual advantages. POS tagging results showed a similar pattern, with accuracy dropping notably on Achhami data. Large language models also showed comparable weaknesses, with accuracy reductions ranging from 2.9 to 7.0 percent. These findings quantify Kathmandu-centered bias in Nepali NLP and highlight the importance of dialectally diverse training data for building more inclusive and equitable language technologies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dhamala-etal-2026-evaluating">
<titleInfo>
<title>Evaluating Nepali NER and POS Tagging Models on the Achhami Dialect</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samikshya</namePart>
<namePart type="family">Dhamala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rishav</namePart>
<namePart type="family">Beejukchhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subresh</namePart>
<namePart type="family">Thakulla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bikash</namePart>
<namePart type="family">Kadayat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Supriya</namePart>
<namePart type="family">Khadka</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 SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</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">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="given">Rigau</namePart>
<namePart type="family">Claramunt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</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>Nepali Natural Language Processing (NLP) models are typically trained and evaluated on Standard Nepali, which can introduce bias against regional dialects. This study investigates the performance of Named Entity Recognition (NER) and Part-of-Speech (POS) tagging models on Achhami, a Far-Western dialect of Nepal. A parallel corpus of 300 sentence pairs was created, covering news, cultural topics, and everyday conversations. Achhami translations were produced by native speakers to preserve linguistic authenticity. The evaluation compared fine-tuned Transformer models with large language models using zero-shot prompting. Across both tasks, all models showed consistent performance degradation on the Achhami dialect. For NER, F1 scores decreased by 2.12 to 3.97 percent. Claude 3.5 Haiku achieved the best NER performance, while the monolingual NepBertA model unexpectedly outperformed multilingual alternatives, challenging assumptions about multilingual advantages. POS tagging results showed a similar pattern, with accuracy dropping notably on Achhami data. Large language models also showed comparable weaknesses, with accuracy reductions ranging from 2.9 to 7.0 percent. These findings quantify Kathmandu-centered bias in Nepali NLP and highlight the importance of dialectally diverse training data for building more inclusive and equitable language technologies.</abstract>
<identifier type="citekey">dhamala-etal-2026-evaluating</identifier>
<identifier type="doi">10.63317/5hmcq734e4yd</identifier>
<location>
<url>https://aclanthology.org/2026.sigul-1.21/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>210</start>
<end>221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Nepali NER and POS Tagging Models on the Achhami Dialect
%A Dhamala, Samikshya
%A Beejukchhen, Rishav
%A Thakulla, Subresh
%A Kadayat, Bikash
%A Khadka, Supriya
%Y Ojha, Atul Kr.
%Y Sakti, Sakriani
%Y Soria, Claudia
%Y Melero, Maite
%Y McCrae, John P.
%Y Lignos, Constantine
%Y Liu, Chao-Hong
%Y Claramunt, German Rigau
%Y Rehm, Georg
%S Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca, Spain
%F dhamala-etal-2026-evaluating
%X Nepali Natural Language Processing (NLP) models are typically trained and evaluated on Standard Nepali, which can introduce bias against regional dialects. This study investigates the performance of Named Entity Recognition (NER) and Part-of-Speech (POS) tagging models on Achhami, a Far-Western dialect of Nepal. A parallel corpus of 300 sentence pairs was created, covering news, cultural topics, and everyday conversations. Achhami translations were produced by native speakers to preserve linguistic authenticity. The evaluation compared fine-tuned Transformer models with large language models using zero-shot prompting. Across both tasks, all models showed consistent performance degradation on the Achhami dialect. For NER, F1 scores decreased by 2.12 to 3.97 percent. Claude 3.5 Haiku achieved the best NER performance, while the monolingual NepBertA model unexpectedly outperformed multilingual alternatives, challenging assumptions about multilingual advantages. POS tagging results showed a similar pattern, with accuracy dropping notably on Achhami data. Large language models also showed comparable weaknesses, with accuracy reductions ranging from 2.9 to 7.0 percent. These findings quantify Kathmandu-centered bias in Nepali NLP and highlight the importance of dialectally diverse training data for building more inclusive and equitable language technologies.
%R 10.63317/5hmcq734e4yd
%U https://aclanthology.org/2026.sigul-1.21/
%U https://doi.org/10.63317/5hmcq734e4yd
%P 210-221
Markdown (Informal)
[Evaluating Nepali NER and POS Tagging Models on the Achhami Dialect](https://aclanthology.org/2026.sigul-1.21/) (Dhamala et al., SIGUL-EURALI-DCLRL 2026)
ACL
- Samikshya Dhamala, Rishav Beejukchhen, Subresh Thakulla, Bikash Kadayat, and Supriya Khadka. 2026. Evaluating Nepali NER and POS Tagging Models on the Achhami Dialect. In Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages, pages 210–221, Palma, Mallorca, Spain. ELRA Language Resources Association (ELRA).