@inproceedings{pokharel-agrawal-2025-nediom,
title = "ne{DIOM}: Dataset and Analysis of {N}epali Idioms",
author = "Pokharel, Rhitabrat and
Agrawal, Ameeta",
editor = "Sarveswaran, Kengatharaiyer and
Vaidya, Ashwini and
Krishna Bal, Bal and
Shams, Sana and
Thapa, Surendrabikram",
booktitle = "Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2025.chipsal-1.16/",
pages = "160--171",
abstract = "Idioms, integral to any language, convey nuanced meanings and cultural references. However, beyond English, few resources exist to support any meaningful exploration of this unique linguistic phenomenon. To facilitate such an inquiry in a low resource language, we introduce a novel dataset of Nepali idioms and the sentences in which these naturally appear. We describe the methodology of creating this resource as well as discuss some of the challenges we encountered. The results of our empirical analysis under various settings using four distinct multilingual models consistently highlight the difficulties these models face in processing Nepali figurative language. Even fine-tuning the models yields limited benefits. Interestingly, the larger models from the BLOOM family of models failed to consistently outperform the smaller models. Overall, we hope that this new resource will facilitate further development of models that can support processing of idiomatic expressions in low resource languages such as Nepali."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pokharel-agrawal-2025-nediom">
<titleInfo>
<title>neDIOM: Dataset and Analysis of Nepali Idioms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rhitabrat</namePart>
<namePart type="family">Pokharel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ameeta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kengatharaiyer</namePart>
<namePart type="family">Sarveswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwini</namePart>
<namePart type="family">Vaidya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bal</namePart>
<namePart type="family">Krishna Bal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sana</namePart>
<namePart type="family">Shams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Idioms, integral to any language, convey nuanced meanings and cultural references. However, beyond English, few resources exist to support any meaningful exploration of this unique linguistic phenomenon. To facilitate such an inquiry in a low resource language, we introduce a novel dataset of Nepali idioms and the sentences in which these naturally appear. We describe the methodology of creating this resource as well as discuss some of the challenges we encountered. The results of our empirical analysis under various settings using four distinct multilingual models consistently highlight the difficulties these models face in processing Nepali figurative language. Even fine-tuning the models yields limited benefits. Interestingly, the larger models from the BLOOM family of models failed to consistently outperform the smaller models. Overall, we hope that this new resource will facilitate further development of models that can support processing of idiomatic expressions in low resource languages such as Nepali.</abstract>
<identifier type="citekey">pokharel-agrawal-2025-nediom</identifier>
<location>
<url>https://aclanthology.org/2025.chipsal-1.16/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>160</start>
<end>171</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T neDIOM: Dataset and Analysis of Nepali Idioms
%A Pokharel, Rhitabrat
%A Agrawal, Ameeta
%Y Sarveswaran, Kengatharaiyer
%Y Vaidya, Ashwini
%Y Krishna Bal, Bal
%Y Shams, Sana
%Y Thapa, Surendrabikram
%S Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)
%D 2025
%8 January
%I International Committee on Computational Linguistics
%C Abu Dhabi, UAE
%F pokharel-agrawal-2025-nediom
%X Idioms, integral to any language, convey nuanced meanings and cultural references. However, beyond English, few resources exist to support any meaningful exploration of this unique linguistic phenomenon. To facilitate such an inquiry in a low resource language, we introduce a novel dataset of Nepali idioms and the sentences in which these naturally appear. We describe the methodology of creating this resource as well as discuss some of the challenges we encountered. The results of our empirical analysis under various settings using four distinct multilingual models consistently highlight the difficulties these models face in processing Nepali figurative language. Even fine-tuning the models yields limited benefits. Interestingly, the larger models from the BLOOM family of models failed to consistently outperform the smaller models. Overall, we hope that this new resource will facilitate further development of models that can support processing of idiomatic expressions in low resource languages such as Nepali.
%U https://aclanthology.org/2025.chipsal-1.16/
%P 160-171
Markdown (Informal)
[neDIOM: Dataset and Analysis of Nepali Idioms](https://aclanthology.org/2025.chipsal-1.16/) (Pokharel & Agrawal, CHiPSAL 2025)
ACL
- Rhitabrat Pokharel and Ameeta Agrawal. 2025. neDIOM: Dataset and Analysis of Nepali Idioms. In Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025), pages 160–171, Abu Dhabi, UAE. International Committee on Computational Linguistics.