@inproceedings{alex-eponon-etal-2024-pinealai,
title = "{P}inealai{\_}{S}tress{I}dent{\_}{LT}-{EDI}@{EACL}2024: Minimal configurations for Stress Identification in {T}amil and {T}elugu",
author = "Alex Eponon, Anvi and
Batyrshin, Ildar and
Sidorov, Grigori",
editor = {Chakravarthi, Bharathi Raja and
B, Bharathi and
Buitelaar, Paul and
Durairaj, Thenmozhi and
Kov{\'a}cs, Gy{\"o}rgy and
Garc{\'\i}a Cumbreras, Miguel {\'A}ngel},
booktitle = "Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion",
month = mar,
year = "2024",
address = "St. Julian's, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.ltedi-1.15",
pages = "152--156",
abstract = "This paper introduces an approach to stress identification in Tamil and Telugu, leveraging traditional machine learning models{---}Fasttext for Tamil and Naive Bayes for Telugu{---}yielding commendable results. The study highlights the scarcity of annotated data and recognizes limitations in phonetic features relevant to these languages, impacting precise information extraction. Our models achieved a macro F1 score of 0.77 for Tamil and 0.72 for Telugu with Fasttext and Naive Bayes, respectively. While the Telugu model secured the second rank in shared tasks, ongoing research is crucial to unlocking the full potential of stress identification in these languages, necessitating the exploration of additional features and advanced techniques specified in the discussions and limitations section.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alex-eponon-etal-2024-pinealai">
<titleInfo>
<title>Pinealai_StressIdent_LT-EDI@EACL2024: Minimal configurations for Stress Identification in Tamil and Telugu</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anvi</namePart>
<namePart type="family">Alex Eponon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ildar</namePart>
<namePart type="family">Batyrshin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grigori</namePart>
<namePart type="family">Sidorov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="family">B</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Buitelaar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thenmozhi</namePart>
<namePart type="family">Durairaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">György</namePart>
<namePart type="family">Kovács</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="given">Ángel</namePart>
<namePart type="family">García Cumbreras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces an approach to stress identification in Tamil and Telugu, leveraging traditional machine learning models—Fasttext for Tamil and Naive Bayes for Telugu—yielding commendable results. The study highlights the scarcity of annotated data and recognizes limitations in phonetic features relevant to these languages, impacting precise information extraction. Our models achieved a macro F1 score of 0.77 for Tamil and 0.72 for Telugu with Fasttext and Naive Bayes, respectively. While the Telugu model secured the second rank in shared tasks, ongoing research is crucial to unlocking the full potential of stress identification in these languages, necessitating the exploration of additional features and advanced techniques specified in the discussions and limitations section.</abstract>
<identifier type="citekey">alex-eponon-etal-2024-pinealai</identifier>
<location>
<url>https://aclanthology.org/2024.ltedi-1.15</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>152</start>
<end>156</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pinealai_StressIdent_LT-EDI@EACL2024: Minimal configurations for Stress Identification in Tamil and Telugu
%A Alex Eponon, Anvi
%A Batyrshin, Ildar
%A Sidorov, Grigori
%Y Chakravarthi, Bharathi Raja
%Y B, Bharathi
%Y Buitelaar, Paul
%Y Durairaj, Thenmozhi
%Y Kovács, György
%Y García Cumbreras, Miguel Ángel
%S Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F alex-eponon-etal-2024-pinealai
%X This paper introduces an approach to stress identification in Tamil and Telugu, leveraging traditional machine learning models—Fasttext for Tamil and Naive Bayes for Telugu—yielding commendable results. The study highlights the scarcity of annotated data and recognizes limitations in phonetic features relevant to these languages, impacting precise information extraction. Our models achieved a macro F1 score of 0.77 for Tamil and 0.72 for Telugu with Fasttext and Naive Bayes, respectively. While the Telugu model secured the second rank in shared tasks, ongoing research is crucial to unlocking the full potential of stress identification in these languages, necessitating the exploration of additional features and advanced techniques specified in the discussions and limitations section.
%U https://aclanthology.org/2024.ltedi-1.15
%P 152-156
Markdown (Informal)
[Pinealai_StressIdent_LT-EDI@EACL2024: Minimal configurations for Stress Identification in Tamil and Telugu](https://aclanthology.org/2024.ltedi-1.15) (Alex Eponon et al., LTEDI-WS 2024)
ACL