@inproceedings{ravikiran-chakravarthi-2022-zero,
title = "Zero-shot Code-Mixed Offensive Span Identification through Rationale Extraction",
author = "Ravikiran, Manikandan and
Chakravarthi, Bharathi Raja",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Krishnamurthy, Parameswari and
Sherly, Elizabeth and
Mahesan, Sinnathamby",
booktitle = "Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.dravidianlangtech-1.37",
doi = "10.18653/v1/2022.dravidianlangtech-1.37",
pages = "240--247",
abstract = "This paper investigates the effectiveness of sentence-level transformers for zero-shot offensive span identification on a code-mixed Tamil dataset. More specifically, we evaluate rationale extraction methods of Local Interpretable Model Agnostic Explanations (LIME) (CITATION) and Integrated Gradients (IG) (CITATION) for adapting transformer based offensive language classification models for zero-shot offensive span identification. To this end, we find that LIME and IG show baseline $F_{1}$ of 26.35{\%} and 44.83{\%}, respectively. Besides, we study the effect of data set size and training process on the overall accuracy of span identification. As a result, we find both LIME and IG to show significant improvement with Masked Data Augmentation and Multilabel Training, with $F_{1}$ of 50.23{\%} and 47.38{\%} respectively. \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 are used to emphasize only the linguistic research challenges.}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ravikiran-chakravarthi-2022-zero">
<titleInfo>
<title>Zero-shot Code-Mixed Offensive Span Identification through Rationale Extraction</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>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages</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">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">Madasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</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>
<name type="personal">
<namePart type="given">Sinnathamby</namePart>
<namePart type="family">Mahesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper investigates the effectiveness of sentence-level transformers for zero-shot offensive span identification on a code-mixed Tamil dataset. More specifically, we evaluate rationale extraction methods of Local Interpretable Model Agnostic Explanations (LIME) (CITATION) and Integrated Gradients (IG) (CITATION) for adapting transformer based offensive language classification models for zero-shot offensive span identification. To this end, we find that LIME and IG show baseline F₁ of 26.35% and 44.83%, respectively. Besides, we study the effect of data set size and training process on the overall accuracy of span identification. As a result, we find both LIME and IG to show significant improvement with Masked Data Augmentation and Multilabel Training, with F₁ of 50.23% and 47.38% respectively. 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 are used to emphasize only the linguistic research challenges.</abstract>
<identifier type="citekey">ravikiran-chakravarthi-2022-zero</identifier>
<identifier type="doi">10.18653/v1/2022.dravidianlangtech-1.37</identifier>
<location>
<url>https://aclanthology.org/2022.dravidianlangtech-1.37</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>240</start>
<end>247</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero-shot Code-Mixed Offensive Span Identification through Rationale Extraction
%A Ravikiran, Manikandan
%A Chakravarthi, Bharathi Raja
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Krishnamurthy, Parameswari
%Y Sherly, Elizabeth
%Y Mahesan, Sinnathamby
%S Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F ravikiran-chakravarthi-2022-zero
%X This paper investigates the effectiveness of sentence-level transformers for zero-shot offensive span identification on a code-mixed Tamil dataset. More specifically, we evaluate rationale extraction methods of Local Interpretable Model Agnostic Explanations (LIME) (CITATION) and Integrated Gradients (IG) (CITATION) for adapting transformer based offensive language classification models for zero-shot offensive span identification. To this end, we find that LIME and IG show baseline F₁ of 26.35% and 44.83%, respectively. Besides, we study the effect of data set size and training process on the overall accuracy of span identification. As a result, we find both LIME and IG to show significant improvement with Masked Data Augmentation and Multilabel Training, with F₁ of 50.23% and 47.38% respectively. 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 are used to emphasize only the linguistic research challenges.
%R 10.18653/v1/2022.dravidianlangtech-1.37
%U https://aclanthology.org/2022.dravidianlangtech-1.37
%U https://doi.org/10.18653/v1/2022.dravidianlangtech-1.37
%P 240-247
Markdown (Informal)
[Zero-shot Code-Mixed Offensive Span Identification through Rationale Extraction](https://aclanthology.org/2022.dravidianlangtech-1.37) (Ravikiran & Chakravarthi, DravidianLangTech 2022)
ACL