@inproceedings{n-j-etal-2025-levos,
title = "{LEVOS}: Leveraging Vocabulary Overlap with {S}anskrit to Generate Technical Lexicons in {I}ndian Languages",
author = "N J, Karthika and
Bhatt, Krishnakant and
Ramakrishnan, Ganesh and
Jyothi, Preethi",
editor = {Kochmar, Ekaterina and
Alhafni, Bashar and
Bexte, Marie and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Tack, Ana{\"i}s and
Yaneva, Victoria and
Yuan, Zheng},
booktitle = "Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.bea-1.20/",
doi = "10.18653/v1/2025.bea-1.20",
pages = "258--265",
ISBN = "979-8-89176-270-1",
abstract = "Translating technical terms into lexically similar, low-resource Indian languages remains a challenge due to limited parallel data and the complexity of linguistic structures. We propose a novel use-case of Sanskrit-based segments for linguistically informed translation of such terms, leveraging subword-level similarity and morphological alignment across related languages. Our approach uses character-level segmentation to identify meaningful subword units, facilitating more accurate and context-aware translation. To enable this, we utilize a Character-level Transformer model for Sanskrit Word Segmentation (CharSS), which addresses the complexities of sandhi and morpho-phonemic changes during segmentation. We observe consistent improvements in two experimental settings for technical term translation using Sanskrit-derived segments, averaging 8.46 and 6.79 chrF++ scores, respectively. Further, we conduct a post hoc human evaluation to verify the quality assessment of the translated technical terms using automated metrics. This work has important implications for the education field, especially in creating accessible, high-quality learning materials in Indian languages. By supporting the accurate and linguistically rooted translation of technical content, our approach facilitates inclusivity and aids in bridging the resource gap for learners in low-resource language communities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="n-j-etal-2025-levos">
<titleInfo>
<title>LEVOS: Leveraging Vocabulary Overlap with Sanskrit to Generate Technical Lexicons in Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karthika</namePart>
<namePart type="family">N J</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krishnakant</namePart>
<namePart type="family">Bhatt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ganesh</namePart>
<namePart type="family">Ramakrishnan</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>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Bexte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-270-1</identifier>
</relatedItem>
<abstract>Translating technical terms into lexically similar, low-resource Indian languages remains a challenge due to limited parallel data and the complexity of linguistic structures. We propose a novel use-case of Sanskrit-based segments for linguistically informed translation of such terms, leveraging subword-level similarity and morphological alignment across related languages. Our approach uses character-level segmentation to identify meaningful subword units, facilitating more accurate and context-aware translation. To enable this, we utilize a Character-level Transformer model for Sanskrit Word Segmentation (CharSS), which addresses the complexities of sandhi and morpho-phonemic changes during segmentation. We observe consistent improvements in two experimental settings for technical term translation using Sanskrit-derived segments, averaging 8.46 and 6.79 chrF++ scores, respectively. Further, we conduct a post hoc human evaluation to verify the quality assessment of the translated technical terms using automated metrics. This work has important implications for the education field, especially in creating accessible, high-quality learning materials in Indian languages. By supporting the accurate and linguistically rooted translation of technical content, our approach facilitates inclusivity and aids in bridging the resource gap for learners in low-resource language communities.</abstract>
<identifier type="citekey">n-j-etal-2025-levos</identifier>
<identifier type="doi">10.18653/v1/2025.bea-1.20</identifier>
<location>
<url>https://aclanthology.org/2025.bea-1.20/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>258</start>
<end>265</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LEVOS: Leveraging Vocabulary Overlap with Sanskrit to Generate Technical Lexicons in Indian Languages
%A N J, Karthika
%A Bhatt, Krishnakant
%A Ramakrishnan, Ganesh
%A Jyothi, Preethi
%Y Kochmar, Ekaterina
%Y Alhafni, Bashar
%Y Bexte, Marie
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%S Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-270-1
%F n-j-etal-2025-levos
%X Translating technical terms into lexically similar, low-resource Indian languages remains a challenge due to limited parallel data and the complexity of linguistic structures. We propose a novel use-case of Sanskrit-based segments for linguistically informed translation of such terms, leveraging subword-level similarity and morphological alignment across related languages. Our approach uses character-level segmentation to identify meaningful subword units, facilitating more accurate and context-aware translation. To enable this, we utilize a Character-level Transformer model for Sanskrit Word Segmentation (CharSS), which addresses the complexities of sandhi and morpho-phonemic changes during segmentation. We observe consistent improvements in two experimental settings for technical term translation using Sanskrit-derived segments, averaging 8.46 and 6.79 chrF++ scores, respectively. Further, we conduct a post hoc human evaluation to verify the quality assessment of the translated technical terms using automated metrics. This work has important implications for the education field, especially in creating accessible, high-quality learning materials in Indian languages. By supporting the accurate and linguistically rooted translation of technical content, our approach facilitates inclusivity and aids in bridging the resource gap for learners in low-resource language communities.
%R 10.18653/v1/2025.bea-1.20
%U https://aclanthology.org/2025.bea-1.20/
%U https://doi.org/10.18653/v1/2025.bea-1.20
%P 258-265
Markdown (Informal)
[LEVOS: Leveraging Vocabulary Overlap with Sanskrit to Generate Technical Lexicons in Indian Languages](https://aclanthology.org/2025.bea-1.20/) (N J et al., BEA 2025)
ACL