@inproceedings{hankins-2024-optimizing,
title = "Optimizing Multilingual Euphemism Detection using Low-Rank Adaption Within and Across Languages",
author = "Hankins, Nicholas",
editor = "Ghosh, Debanjan and
Muresan, Smaranda and
Feldman, Anna and
Chakrabarty, Tuhin and
Liu, Emmy",
booktitle = "Proceedings of the 4th Workshop on Figurative Language Processing (FigLang 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.figlang-1.2",
doi = "10.18653/v1/2024.figlang-1.2",
pages = "8--14",
abstract = "This short paper presents an investigation into the effectiveness of various classification methods as a submission in the Multilingual Euphemism Detection Shared Task for the Fourth Workshop on Figurative Language Processing co-located with NAACL 2024. The process used by the participant utilizes pre-trained large language models combined with parameter efficient fine-tuning methods, specifically Low-Rank Adaptation (LoRA), in classifying euphemisms across four different languages - Mandarin Chinese, American English, Spanish, and Yor{\`u}b{\'a}. The study is comprised of three main components that aim to explore heuristic methods to navigate how base models can most efficiently be fine-tuned into classifiers to learn figurative language. Multilingual labeled training data was utilized to fine-tune classifiers for each language, and later combined for one large classifier, while unseen test data was finally used to evaluate the accuracy of the best performing classifiers. In addition, cross-lingual tests were conducted by applying each language{'}s data on each of the other language{'}s classifiers. All of the results provide insights into the potential of pre-trained base models combined with LoRA fine-tuning methods in accurately classifying euphemisms across and within different languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hankins-2024-optimizing">
<titleInfo>
<title>Optimizing Multilingual Euphemism Detection using Low-Rank Adaption Within and Across Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Hankins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Figurative Language Processing (FigLang 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tuhin</namePart>
<namePart type="family">Chakrabarty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This short paper presents an investigation into the effectiveness of various classification methods as a submission in the Multilingual Euphemism Detection Shared Task for the Fourth Workshop on Figurative Language Processing co-located with NAACL 2024. The process used by the participant utilizes pre-trained large language models combined with parameter efficient fine-tuning methods, specifically Low-Rank Adaptation (LoRA), in classifying euphemisms across four different languages - Mandarin Chinese, American English, Spanish, and Yorùbá. The study is comprised of three main components that aim to explore heuristic methods to navigate how base models can most efficiently be fine-tuned into classifiers to learn figurative language. Multilingual labeled training data was utilized to fine-tune classifiers for each language, and later combined for one large classifier, while unseen test data was finally used to evaluate the accuracy of the best performing classifiers. In addition, cross-lingual tests were conducted by applying each language’s data on each of the other language’s classifiers. All of the results provide insights into the potential of pre-trained base models combined with LoRA fine-tuning methods in accurately classifying euphemisms across and within different languages.</abstract>
<identifier type="citekey">hankins-2024-optimizing</identifier>
<identifier type="doi">10.18653/v1/2024.figlang-1.2</identifier>
<location>
<url>https://aclanthology.org/2024.figlang-1.2</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>8</start>
<end>14</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Optimizing Multilingual Euphemism Detection using Low-Rank Adaption Within and Across Languages
%A Hankins, Nicholas
%Y Ghosh, Debanjan
%Y Muresan, Smaranda
%Y Feldman, Anna
%Y Chakrabarty, Tuhin
%Y Liu, Emmy
%S Proceedings of the 4th Workshop on Figurative Language Processing (FigLang 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico (Hybrid)
%F hankins-2024-optimizing
%X This short paper presents an investigation into the effectiveness of various classification methods as a submission in the Multilingual Euphemism Detection Shared Task for the Fourth Workshop on Figurative Language Processing co-located with NAACL 2024. The process used by the participant utilizes pre-trained large language models combined with parameter efficient fine-tuning methods, specifically Low-Rank Adaptation (LoRA), in classifying euphemisms across four different languages - Mandarin Chinese, American English, Spanish, and Yorùbá. The study is comprised of three main components that aim to explore heuristic methods to navigate how base models can most efficiently be fine-tuned into classifiers to learn figurative language. Multilingual labeled training data was utilized to fine-tune classifiers for each language, and later combined for one large classifier, while unseen test data was finally used to evaluate the accuracy of the best performing classifiers. In addition, cross-lingual tests were conducted by applying each language’s data on each of the other language’s classifiers. All of the results provide insights into the potential of pre-trained base models combined with LoRA fine-tuning methods in accurately classifying euphemisms across and within different languages.
%R 10.18653/v1/2024.figlang-1.2
%U https://aclanthology.org/2024.figlang-1.2
%U https://doi.org/10.18653/v1/2024.figlang-1.2
%P 8-14
Markdown (Informal)
[Optimizing Multilingual Euphemism Detection using Low-Rank Adaption Within and Across Languages](https://aclanthology.org/2024.figlang-1.2) (Hankins, Fig-Lang-WS 2024)
ACL