@inproceedings{mohapatra-etal-2020-incorporating,
title = "Incorporating Localised Context in {W}ordnet for Indic Languages",
author = "Mohapatra, Soumya and
Agnihotri, Shikhar and
Garg, Apar and
Shah, Praveen and
Chakraverty, Shampa",
editor = "Declerk, Thierry and
Gonzalez-Dios, Itziar and
Rigau, German",
booktitle = "Proceedings of the LREC 2020 Workshop on Multimodal Wordnets (MMW2020)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "The European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2020.mmw-1.2",
pages = "7--13",
abstract = "Due to rapid urbanization and a homogenized medium of instruction imposed in educational institutions, we have lost much of the golden literary offerings of the diverse languages and dialects that India once possessed. There is an urgent need to mitigate the paucity of online linguistic resources for several Hindi dialects. Given the corpus of a dialect, our system integrates the vocabulary of the dialect to the synsets of IndoWordnet along with their corresponding meta-data. Furthermore, we propose a systematic method for generating exemplary sentences for each newly integrated dialect word. The vocabulary thus integrated follows the schema of the wordnet and generates exemplary sentences to illustrate the meaning and usage of the word. We illustrate our methodology with the integration of words in the Awadhi dialect to the Hindi IndoWordnet to achieve an enrichment of 11.68 {\%} to the existing Hindi synsets. The BLEU metric for evaluating the quality of sentences yielded a 75th percentile score of 0.6351.",
language = "English",
ISBN = "979-10-95546-41-2",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohapatra-etal-2020-incorporating">
<titleInfo>
<title>Incorporating Localised Context in Wordnet for Indic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Soumya</namePart>
<namePart type="family">Mohapatra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikhar</namePart>
<namePart type="family">Agnihotri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apar</namePart>
<namePart type="family">Garg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Praveen</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shampa</namePart>
<namePart type="family">Chakraverty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the LREC 2020 Workshop on Multimodal Wordnets (MMW2020)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Itziar</namePart>
<namePart type="family">Gonzalez-Dios</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-41-2</identifier>
</relatedItem>
<abstract>Due to rapid urbanization and a homogenized medium of instruction imposed in educational institutions, we have lost much of the golden literary offerings of the diverse languages and dialects that India once possessed. There is an urgent need to mitigate the paucity of online linguistic resources for several Hindi dialects. Given the corpus of a dialect, our system integrates the vocabulary of the dialect to the synsets of IndoWordnet along with their corresponding meta-data. Furthermore, we propose a systematic method for generating exemplary sentences for each newly integrated dialect word. The vocabulary thus integrated follows the schema of the wordnet and generates exemplary sentences to illustrate the meaning and usage of the word. We illustrate our methodology with the integration of words in the Awadhi dialect to the Hindi IndoWordnet to achieve an enrichment of 11.68 % to the existing Hindi synsets. The BLEU metric for evaluating the quality of sentences yielded a 75th percentile score of 0.6351.</abstract>
<identifier type="citekey">mohapatra-etal-2020-incorporating</identifier>
<location>
<url>https://aclanthology.org/2020.mmw-1.2</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>7</start>
<end>13</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incorporating Localised Context in Wordnet for Indic Languages
%A Mohapatra, Soumya
%A Agnihotri, Shikhar
%A Garg, Apar
%A Shah, Praveen
%A Chakraverty, Shampa
%Y Declerk, Thierry
%Y Gonzalez-Dios, Itziar
%Y Rigau, German
%S Proceedings of the LREC 2020 Workshop on Multimodal Wordnets (MMW2020)
%D 2020
%8 May
%I The European Language Resources Association (ELRA)
%C Marseille, France
%@ 979-10-95546-41-2
%G English
%F mohapatra-etal-2020-incorporating
%X Due to rapid urbanization and a homogenized medium of instruction imposed in educational institutions, we have lost much of the golden literary offerings of the diverse languages and dialects that India once possessed. There is an urgent need to mitigate the paucity of online linguistic resources for several Hindi dialects. Given the corpus of a dialect, our system integrates the vocabulary of the dialect to the synsets of IndoWordnet along with their corresponding meta-data. Furthermore, we propose a systematic method for generating exemplary sentences for each newly integrated dialect word. The vocabulary thus integrated follows the schema of the wordnet and generates exemplary sentences to illustrate the meaning and usage of the word. We illustrate our methodology with the integration of words in the Awadhi dialect to the Hindi IndoWordnet to achieve an enrichment of 11.68 % to the existing Hindi synsets. The BLEU metric for evaluating the quality of sentences yielded a 75th percentile score of 0.6351.
%U https://aclanthology.org/2020.mmw-1.2
%P 7-13
Markdown (Informal)
[Incorporating Localised Context in Wordnet for Indic Languages](https://aclanthology.org/2020.mmw-1.2) (Mohapatra et al., MMW 2020)
ACL
- Soumya Mohapatra, Shikhar Agnihotri, Apar Garg, Praveen Shah, and Shampa Chakraverty. 2020. Incorporating Localised Context in Wordnet for Indic Languages. In Proceedings of the LREC 2020 Workshop on Multimodal Wordnets (MMW2020), pages 7–13, Marseille, France. The European Language Resources Association (ELRA).