@inproceedings{redkar-etal-2026-konkani,
title = "{K}onkani {W}ordnet Resources",
author = "Redkar, Hanumant H. and
Gawas, Mahadev and
Desai, Anjali and
Pawar, 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-1.6/",
doi = "10.63317/2sswqmbnfws3",
pages = "49--54",
abstract = "Konkani is a low-resource Indo-Aryan language spoken along the western coast of India, characterized by significant dialectal variation, multi-script usage, and limited standardized computational resources. This paper presents a consolidated and analysis-ready lexical resource derived from the Konkani Wordnet, built under the IndoWordNet framework. The resource comprises 32,370 synsets, 37,719 unique lexical entries, 32,370 glosses, and 33,318 example sentences, enriched with pronunciations, semantic relations, and illustrative examples. We describe the systematic extraction, normalization, and structural integration of wordnet data, resolving identifier inconsistencies and ensuring semantic coherence across distributed lexical files. To demonstrate the practical utility of this resource, we present an API-based bilingual vocabulary exercise generation system that leverages shared synset identifiers to automatically produce semantically aligned Hindi{--}Konkani word pairs for e-learning applications. The resulting resource enhances accessibility, reproducibility, and computational readiness for NLP tasks, while providing a foundational infrastructure for developing technology-driven teaching and learning tools for Konkani."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="redkar-etal-2026-konkani">
<titleInfo>
<title>Konkani Wordnet Resources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanumant</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Redkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahadev</namePart>
<namePart type="family">Gawas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anjali</namePart>
<namePart type="family">Desai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jyoti</namePart>
<namePart type="family">Pawar</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>Konkani is a low-resource Indo-Aryan language spoken along the western coast of India, characterized by significant dialectal variation, multi-script usage, and limited standardized computational resources. This paper presents a consolidated and analysis-ready lexical resource derived from the Konkani Wordnet, built under the IndoWordNet framework. The resource comprises 32,370 synsets, 37,719 unique lexical entries, 32,370 glosses, and 33,318 example sentences, enriched with pronunciations, semantic relations, and illustrative examples. We describe the systematic extraction, normalization, and structural integration of wordnet data, resolving identifier inconsistencies and ensuring semantic coherence across distributed lexical files. To demonstrate the practical utility of this resource, we present an API-based bilingual vocabulary exercise generation system that leverages shared synset identifiers to automatically produce semantically aligned Hindi–Konkani word pairs for e-learning applications. The resulting resource enhances accessibility, reproducibility, and computational readiness for NLP tasks, while providing a foundational infrastructure for developing technology-driven teaching and learning tools for Konkani.</abstract>
<identifier type="citekey">redkar-etal-2026-konkani</identifier>
<identifier type="doi">10.63317/2sswqmbnfws3</identifier>
<location>
<url>https://aclanthology.org/2026.wildre-1.6/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>49</start>
<end>54</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Konkani Wordnet Resources
%A Redkar, Hanumant H.
%A Gawas, Mahadev
%A Desai, Anjali
%A Pawar, 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 redkar-etal-2026-konkani
%X Konkani is a low-resource Indo-Aryan language spoken along the western coast of India, characterized by significant dialectal variation, multi-script usage, and limited standardized computational resources. This paper presents a consolidated and analysis-ready lexical resource derived from the Konkani Wordnet, built under the IndoWordNet framework. The resource comprises 32,370 synsets, 37,719 unique lexical entries, 32,370 glosses, and 33,318 example sentences, enriched with pronunciations, semantic relations, and illustrative examples. We describe the systematic extraction, normalization, and structural integration of wordnet data, resolving identifier inconsistencies and ensuring semantic coherence across distributed lexical files. To demonstrate the practical utility of this resource, we present an API-based bilingual vocabulary exercise generation system that leverages shared synset identifiers to automatically produce semantically aligned Hindi–Konkani word pairs for e-learning applications. The resulting resource enhances accessibility, reproducibility, and computational readiness for NLP tasks, while providing a foundational infrastructure for developing technology-driven teaching and learning tools for Konkani.
%R 10.63317/2sswqmbnfws3
%U https://aclanthology.org/2026.wildre-1.6/
%U https://doi.org/10.63317/2sswqmbnfws3
%P 49-54
Markdown (Informal)
[Konkani Wordnet Resources](https://aclanthology.org/2026.wildre-1.6/) (Redkar et al., WILDRE 2026)
ACL
- Hanumant H. Redkar, Mahadev Gawas, Anjali Desai, and Jyoti Pawar. 2026. Konkani Wordnet Resources. In Proceedings of the 8th Workshop on Indian Language Data: Resources and Evaluation, pages 49–54, Palma, Mallorca, Spain. ELRA Language Resources Association (ELRA).