@inproceedings{maheshwari-etal-2025-lexgen,
title = "{L}ex{G}en: Domain-aware Multilingual Lexicon Generation",
author = "Maheshwari, Ayush and
Singh, Atul Kumar and
Karthika, N J and
Bhatt, Krishnakant and
Jyothi, Preethi and
Ramakrishnan, Ganesh",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.365/",
doi = "10.18653/v1/2025.acl-long.365",
pages = "7364--7375",
ISBN = "979-8-89176-251-0",
abstract = "Lexicon or dictionary generation across domains has the potential for societal impact, as it can potentially enhance information accessibility for a diverse user base while preserving language identity. Prior work in the field primarily focuses on bilingual lexical induction, which deals with word alignments using mapping-based or corpora-based approaches. However, these approaches do not cater to domain-specific lexicon generation that consists of domain-specific terminology. This task becomes particularly important in specialized medical, engineering, and other technical domains, owing to the highly infrequent usage of the terms and scarcity of data involving domain-specific terms especially for low-resource languages. We propose a new model to generate dictionary words for 6 Indian languages in the multi-domain setting. Our model consists of domain-specific and domain-generic layers that encode information, and these layers are invoked via a learnable routing technique. We also release a new benchmark dataset consisting of {\ensuremath{>}}75K translation pairs across 6 Indian languages spanning 8 diverse domains. We conduct both zero-shot and few-shot experiments across multiple domains to show the efficacy of our proposed model in generalizing to unseen domains and unseen languages. Additionally, we also perform a human post-hoc evaluation on unseen languages. The source code and dataset is present at https://github.com/Atulkmrsingh/lexgen."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maheshwari-etal-2025-lexgen">
<titleInfo>
<title>LexGen: Domain-aware Multilingual Lexicon Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ayush</namePart>
<namePart type="family">Maheshwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">N</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Karthika</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">Preethi</namePart>
<namePart type="family">Jyothi</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>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</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">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Lexicon or dictionary generation across domains has the potential for societal impact, as it can potentially enhance information accessibility for a diverse user base while preserving language identity. Prior work in the field primarily focuses on bilingual lexical induction, which deals with word alignments using mapping-based or corpora-based approaches. However, these approaches do not cater to domain-specific lexicon generation that consists of domain-specific terminology. This task becomes particularly important in specialized medical, engineering, and other technical domains, owing to the highly infrequent usage of the terms and scarcity of data involving domain-specific terms especially for low-resource languages. We propose a new model to generate dictionary words for 6 Indian languages in the multi-domain setting. Our model consists of domain-specific and domain-generic layers that encode information, and these layers are invoked via a learnable routing technique. We also release a new benchmark dataset consisting of \ensuremath>75K translation pairs across 6 Indian languages spanning 8 diverse domains. We conduct both zero-shot and few-shot experiments across multiple domains to show the efficacy of our proposed model in generalizing to unseen domains and unseen languages. Additionally, we also perform a human post-hoc evaluation on unseen languages. The source code and dataset is present at https://github.com/Atulkmrsingh/lexgen.</abstract>
<identifier type="citekey">maheshwari-etal-2025-lexgen</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.365</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.365/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>7364</start>
<end>7375</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LexGen: Domain-aware Multilingual Lexicon Generation
%A Maheshwari, Ayush
%A Singh, Atul Kumar
%A Karthika, N. J.
%A Bhatt, Krishnakant
%A Jyothi, Preethi
%A Ramakrishnan, Ganesh
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F maheshwari-etal-2025-lexgen
%X Lexicon or dictionary generation across domains has the potential for societal impact, as it can potentially enhance information accessibility for a diverse user base while preserving language identity. Prior work in the field primarily focuses on bilingual lexical induction, which deals with word alignments using mapping-based or corpora-based approaches. However, these approaches do not cater to domain-specific lexicon generation that consists of domain-specific terminology. This task becomes particularly important in specialized medical, engineering, and other technical domains, owing to the highly infrequent usage of the terms and scarcity of data involving domain-specific terms especially for low-resource languages. We propose a new model to generate dictionary words for 6 Indian languages in the multi-domain setting. Our model consists of domain-specific and domain-generic layers that encode information, and these layers are invoked via a learnable routing technique. We also release a new benchmark dataset consisting of \ensuremath>75K translation pairs across 6 Indian languages spanning 8 diverse domains. We conduct both zero-shot and few-shot experiments across multiple domains to show the efficacy of our proposed model in generalizing to unseen domains and unseen languages. Additionally, we also perform a human post-hoc evaluation on unseen languages. The source code and dataset is present at https://github.com/Atulkmrsingh/lexgen.
%R 10.18653/v1/2025.acl-long.365
%U https://aclanthology.org/2025.acl-long.365/
%U https://doi.org/10.18653/v1/2025.acl-long.365
%P 7364-7375
Markdown (Informal)
[LexGen: Domain-aware Multilingual Lexicon Generation](https://aclanthology.org/2025.acl-long.365/) (Maheshwari et al., ACL 2025)
ACL
- Ayush Maheshwari, Atul Kumar Singh, N J Karthika, Krishnakant Bhatt, Preethi Jyothi, and Ganesh Ramakrishnan. 2025. LexGen: Domain-aware Multilingual Lexicon Generation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7364–7375, Vienna, Austria. Association for Computational Linguistics.