@inproceedings{kuwali-shikhar-kumar-2023-pos,
title = "{P}o{S} to {UP}o{S} Conversion and Creation of {UP}o{S} Tagged Resources for {A}ssamese Language",
author = "Kuwali, Talukdar and
Shikhar Kumar, Sarma",
editor = "Jyoti, D. Pawar and
Sobha, Lalitha Devi",
booktitle = "Proceedings of the 20th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2023",
address = "Goa University, Goa, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2023.icon-1.38",
pages = "450--459",
abstract = "This paper addresses the vital task of transitioning from traditional Part-of-Speech (PoS) tagging to Universal Part-of-Speech (UPoS) tagging within the linguistic context of the Assamese language. The paper outlines a comprehensive methodology for PoS to UPoS conversion and the creation of UPoS tagged resources, bridging the gap between localized linguistic analysis and universal standards. The significance of this work lies in its potential to enhance natural language processing and understanding for the Assamese language, contributing to broader multilingual applications. The paper details the data preparation and creation processes, annotation methods, and evaluation techniques, shedding light on the challenges and opportunities presented in the pursuit of linguistic universality. The contents of this research have implications for improving language technology in the Assamese language and can serve as a model for similar work in other regional languages. Mapping of standard PoS tagset applicable for Indian languages to that of the primary categories of the UPoS tagset is done with respect to the Assamese language lexical behaviour. Conversion of PoS tagged text corpus to UPoS taged corpus using this mapping, and then utilizing a Deep Learning based model trained on such a dataset to create a sizable UPoS tagged corpus, are presented in a structured flow. This paper is a step towards a more standardized, universal understanding of linguistic elements in a diverse and multilingual world.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kuwali-shikhar-kumar-2023-pos">
<titleInfo>
<title>PoS to UPoS Conversion and Creation of UPoS Tagged Resources for Assamese Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Talukdar</namePart>
<namePart type="family">Kuwali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarma</namePart>
<namePart type="family">Shikhar Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">D</namePart>
<namePart type="given">Pawar</namePart>
<namePart type="family">Jyoti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lalitha</namePart>
<namePart type="given">Devi</namePart>
<namePart type="family">Sobha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Goa University, Goa, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper addresses the vital task of transitioning from traditional Part-of-Speech (PoS) tagging to Universal Part-of-Speech (UPoS) tagging within the linguistic context of the Assamese language. The paper outlines a comprehensive methodology for PoS to UPoS conversion and the creation of UPoS tagged resources, bridging the gap between localized linguistic analysis and universal standards. The significance of this work lies in its potential to enhance natural language processing and understanding for the Assamese language, contributing to broader multilingual applications. The paper details the data preparation and creation processes, annotation methods, and evaluation techniques, shedding light on the challenges and opportunities presented in the pursuit of linguistic universality. The contents of this research have implications for improving language technology in the Assamese language and can serve as a model for similar work in other regional languages. Mapping of standard PoS tagset applicable for Indian languages to that of the primary categories of the UPoS tagset is done with respect to the Assamese language lexical behaviour. Conversion of PoS tagged text corpus to UPoS taged corpus using this mapping, and then utilizing a Deep Learning based model trained on such a dataset to create a sizable UPoS tagged corpus, are presented in a structured flow. This paper is a step towards a more standardized, universal understanding of linguistic elements in a diverse and multilingual world.</abstract>
<identifier type="citekey">kuwali-shikhar-kumar-2023-pos</identifier>
<location>
<url>https://aclanthology.org/2023.icon-1.38</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>450</start>
<end>459</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PoS to UPoS Conversion and Creation of UPoS Tagged Resources for Assamese Language
%A Kuwali, Talukdar
%A Shikhar Kumar, Sarma
%Y Jyoti, D. Pawar
%Y Sobha, Lalitha Devi
%S Proceedings of the 20th International Conference on Natural Language Processing (ICON)
%D 2023
%8 December
%I NLP Association of India (NLPAI)
%C Goa University, Goa, India
%F kuwali-shikhar-kumar-2023-pos
%X This paper addresses the vital task of transitioning from traditional Part-of-Speech (PoS) tagging to Universal Part-of-Speech (UPoS) tagging within the linguistic context of the Assamese language. The paper outlines a comprehensive methodology for PoS to UPoS conversion and the creation of UPoS tagged resources, bridging the gap between localized linguistic analysis and universal standards. The significance of this work lies in its potential to enhance natural language processing and understanding for the Assamese language, contributing to broader multilingual applications. The paper details the data preparation and creation processes, annotation methods, and evaluation techniques, shedding light on the challenges and opportunities presented in the pursuit of linguistic universality. The contents of this research have implications for improving language technology in the Assamese language and can serve as a model for similar work in other regional languages. Mapping of standard PoS tagset applicable for Indian languages to that of the primary categories of the UPoS tagset is done with respect to the Assamese language lexical behaviour. Conversion of PoS tagged text corpus to UPoS taged corpus using this mapping, and then utilizing a Deep Learning based model trained on such a dataset to create a sizable UPoS tagged corpus, are presented in a structured flow. This paper is a step towards a more standardized, universal understanding of linguistic elements in a diverse and multilingual world.
%U https://aclanthology.org/2023.icon-1.38
%P 450-459
Markdown (Informal)
[PoS to UPoS Conversion and Creation of UPoS Tagged Resources for Assamese Language](https://aclanthology.org/2023.icon-1.38) (Kuwali & Shikhar Kumar, ICON 2023)
ACL