@inproceedings{keh-etal-2022-eureka,
title = "{EUREKA}: {EU}phemism Recognition Enhanced through Knn-based methods and Augmentation",
author = "Keh, Sedrick Scott and
Bharadwaj, Rohit and
Liu, Emmy and
Tedeschi, Simone and
Gangal, Varun and
Navigli, Roberto",
editor = "Ghosh, Debanjan and
Beigman Klebanov, Beata and
Muresan, Smaranda and
Feldman, Anna and
Poria, Soujanya and
Chakrabarty, Tuhin",
booktitle = "Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.flp-1.15",
doi = "10.18653/v1/2022.flp-1.15",
pages = "111--117",
abstract = "We introduce EUREKA, an ensemble-based approach for performing automatic euphemism detection. We (1) identify and correct potentially mislabelled rows in the dataset, (2) curate an expanded corpus called EuphAug, (3) leverage model representations of Potentially Euphemistic Terms (PETs), and (4) explore using representations of semantically close sentences to aid in classification. Using our augmented dataset and kNN-based methods, EUREKA was able to achieve state-of-the-art results on the public leaderboard of the Euphemism Detection Shared Task, ranking first with a macro F1 score of 0.881.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="keh-etal-2022-eureka">
<titleInfo>
<title>EUREKA: EUphemism Recognition Enhanced through Knn-based methods and Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sedrick</namePart>
<namePart type="given">Scott</namePart>
<namePart type="family">Keh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohit</namePart>
<namePart type="family">Bharadwaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Tedeschi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Gangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)</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">Beata</namePart>
<namePart type="family">Beigman Klebanov</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">Soujanya</namePart>
<namePart type="family">Poria</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce EUREKA, an ensemble-based approach for performing automatic euphemism detection. We (1) identify and correct potentially mislabelled rows in the dataset, (2) curate an expanded corpus called EuphAug, (3) leverage model representations of Potentially Euphemistic Terms (PETs), and (4) explore using representations of semantically close sentences to aid in classification. Using our augmented dataset and kNN-based methods, EUREKA was able to achieve state-of-the-art results on the public leaderboard of the Euphemism Detection Shared Task, ranking first with a macro F1 score of 0.881.</abstract>
<identifier type="citekey">keh-etal-2022-eureka</identifier>
<identifier type="doi">10.18653/v1/2022.flp-1.15</identifier>
<location>
<url>https://aclanthology.org/2022.flp-1.15</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>111</start>
<end>117</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EUREKA: EUphemism Recognition Enhanced through Knn-based methods and Augmentation
%A Keh, Sedrick Scott
%A Bharadwaj, Rohit
%A Liu, Emmy
%A Tedeschi, Simone
%A Gangal, Varun
%A Navigli, Roberto
%Y Ghosh, Debanjan
%Y Beigman Klebanov, Beata
%Y Muresan, Smaranda
%Y Feldman, Anna
%Y Poria, Soujanya
%Y Chakrabarty, Tuhin
%S Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F keh-etal-2022-eureka
%X We introduce EUREKA, an ensemble-based approach for performing automatic euphemism detection. We (1) identify and correct potentially mislabelled rows in the dataset, (2) curate an expanded corpus called EuphAug, (3) leverage model representations of Potentially Euphemistic Terms (PETs), and (4) explore using representations of semantically close sentences to aid in classification. Using our augmented dataset and kNN-based methods, EUREKA was able to achieve state-of-the-art results on the public leaderboard of the Euphemism Detection Shared Task, ranking first with a macro F1 score of 0.881.
%R 10.18653/v1/2022.flp-1.15
%U https://aclanthology.org/2022.flp-1.15
%U https://doi.org/10.18653/v1/2022.flp-1.15
%P 111-117
Markdown (Informal)
[EUREKA: EUphemism Recognition Enhanced through Knn-based methods and Augmentation](https://aclanthology.org/2022.flp-1.15) (Keh et al., Fig-Lang 2022)
ACL