@inproceedings{ravikiran-chakravarthi-2023-errors,
title = "On the Errors in Code-Mixed {T}amil-{E}nglish Offensive Span Identification",
author = "Ravikiran, Manikandan and
Chakravarthi, Bharathi Raja",
editor = "Chakravarthi, Bharathi R. and
Priyadharshini, Ruba and
M, Anand Kumar and
Thavareesan, Sajeetha and
Sherly, Elizabeth",
booktitle = "Proceedings of the Third Workshop on Speech and Language Technologies for Dravidian Languages",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.dravidianlangtech-1.1",
pages = "1--9",
abstract = "In recent times, offensive span identification in code-mixed Tamil-English language has seen traction with the release of datasets, shared tasks, and the development of multiple methods. However, the details of various errors shown by these methods are currently unclear. This paper presents a detailed analysis of various errors in state-of-the-art Tamil-English offensive span identification methods. Our study reveals the strengths and weaknesses of the widely used sequence labeling and zero-shot models for offensive span identification. In the due process, we identify data-related errors, improve data annotation and release additional diagnostic data to evaluate models{'} quality and stability. \textit{Disclaimer: This paper contains examples that may be considered profane, vulgar, or offensive. The examples do not represent the views of the authors or their employers/graduate schools towards any person(s), group(s), practice(s), or entity/entities. Instead, they emphasize the complexity of various errors and linguistic research challenges.}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ravikiran-chakravarthi-2023-errors">
<titleInfo>
<title>On the Errors in Code-Mixed Tamil-English Offensive Span Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manikandan</namePart>
<namePart type="family">Ravikiran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Speech and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">M</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sajeetha</namePart>
<namePart type="family">Thavareesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent times, offensive span identification in code-mixed Tamil-English language has seen traction with the release of datasets, shared tasks, and the development of multiple methods. However, the details of various errors shown by these methods are currently unclear. This paper presents a detailed analysis of various errors in state-of-the-art Tamil-English offensive span identification methods. Our study reveals the strengths and weaknesses of the widely used sequence labeling and zero-shot models for offensive span identification. In the due process, we identify data-related errors, improve data annotation and release additional diagnostic data to evaluate models’ quality and stability. Disclaimer: This paper contains examples that may be considered profane, vulgar, or offensive. The examples do not represent the views of the authors or their employers/graduate schools towards any person(s), group(s), practice(s), or entity/entities. Instead, they emphasize the complexity of various errors and linguistic research challenges.</abstract>
<identifier type="citekey">ravikiran-chakravarthi-2023-errors</identifier>
<location>
<url>https://aclanthology.org/2023.dravidianlangtech-1.1</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>1</start>
<end>9</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Errors in Code-Mixed Tamil-English Offensive Span Identification
%A Ravikiran, Manikandan
%A Chakravarthi, Bharathi Raja
%Y Chakravarthi, Bharathi R.
%Y Priyadharshini, Ruba
%Y M, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Sherly, Elizabeth
%S Proceedings of the Third Workshop on Speech and Language Technologies for Dravidian Languages
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F ravikiran-chakravarthi-2023-errors
%X In recent times, offensive span identification in code-mixed Tamil-English language has seen traction with the release of datasets, shared tasks, and the development of multiple methods. However, the details of various errors shown by these methods are currently unclear. This paper presents a detailed analysis of various errors in state-of-the-art Tamil-English offensive span identification methods. Our study reveals the strengths and weaknesses of the widely used sequence labeling and zero-shot models for offensive span identification. In the due process, we identify data-related errors, improve data annotation and release additional diagnostic data to evaluate models’ quality and stability. Disclaimer: This paper contains examples that may be considered profane, vulgar, or offensive. The examples do not represent the views of the authors or their employers/graduate schools towards any person(s), group(s), practice(s), or entity/entities. Instead, they emphasize the complexity of various errors and linguistic research challenges.
%U https://aclanthology.org/2023.dravidianlangtech-1.1
%P 1-9
Markdown (Informal)
[On the Errors in Code-Mixed Tamil-English Offensive Span Identification](https://aclanthology.org/2023.dravidianlangtech-1.1) (Ravikiran & Chakravarthi, DravidianLangTech-WS 2023)
ACL