@inproceedings{wiriyathammabhum-2022-tedb,
title = "{TEDB} System Description to a Shared Task on Euphemism Detection 2022",
author = "Wiriyathammabhum, Peratham",
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-1.1",
doi = "10.18653/v1/2022.flp-1.1",
pages = "1--7",
abstract = "In this report, we describe our Transformers for euphemism detection baseline (TEDB) submissions to a shared task on euphemism detection 2022. We cast the task of predicting euphemism as text classification. We considered Transformer-based models which are the current state-of-the-art methods for text classification. We explored different training schemes, pretrained models, and model architectures. Our best result of 0.816 F1-score (0.818 precision and 0.814 recall) consists of a euphemism-detection-finetuned TweetEval/TimeLMs-pretrained RoBERTa model as a feature extractor frontend with a KimCNN classifier backend trained end-to-end using a cosine annealing scheduler. We observed pretrained models on sentiment analysis and offensiveness detection to correlate with more F1-score while pretraining on other tasks, such as sarcasm detection, produces less F1-scores. Also, putting more word vector channels does not improve the performance in our experiments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wiriyathammabhum-2022-tedb">
<titleInfo>
<title>TEDB System Description to a Shared Task on Euphemism Detection 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peratham</namePart>
<namePart type="family">Wiriyathammabhum</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>In this report, we describe our Transformers for euphemism detection baseline (TEDB) submissions to a shared task on euphemism detection 2022. We cast the task of predicting euphemism as text classification. We considered Transformer-based models which are the current state-of-the-art methods for text classification. We explored different training schemes, pretrained models, and model architectures. Our best result of 0.816 F1-score (0.818 precision and 0.814 recall) consists of a euphemism-detection-finetuned TweetEval/TimeLMs-pretrained RoBERTa model as a feature extractor frontend with a KimCNN classifier backend trained end-to-end using a cosine annealing scheduler. We observed pretrained models on sentiment analysis and offensiveness detection to correlate with more F1-score while pretraining on other tasks, such as sarcasm detection, produces less F1-scores. Also, putting more word vector channels does not improve the performance in our experiments.</abstract>
<identifier type="citekey">wiriyathammabhum-2022-tedb</identifier>
<identifier type="doi">10.18653/v1/2022.flp-1.1</identifier>
<location>
<url>https://aclanthology.org/2022.flp-1.1</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>1</start>
<end>7</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TEDB System Description to a Shared Task on Euphemism Detection 2022
%A Wiriyathammabhum, Peratham
%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 wiriyathammabhum-2022-tedb
%X In this report, we describe our Transformers for euphemism detection baseline (TEDB) submissions to a shared task on euphemism detection 2022. We cast the task of predicting euphemism as text classification. We considered Transformer-based models which are the current state-of-the-art methods for text classification. We explored different training schemes, pretrained models, and model architectures. Our best result of 0.816 F1-score (0.818 precision and 0.814 recall) consists of a euphemism-detection-finetuned TweetEval/TimeLMs-pretrained RoBERTa model as a feature extractor frontend with a KimCNN classifier backend trained end-to-end using a cosine annealing scheduler. We observed pretrained models on sentiment analysis and offensiveness detection to correlate with more F1-score while pretraining on other tasks, such as sarcasm detection, produces less F1-scores. Also, putting more word vector channels does not improve the performance in our experiments.
%R 10.18653/v1/2022.flp-1.1
%U https://aclanthology.org/2022.flp-1.1
%U https://doi.org/10.18653/v1/2022.flp-1.1
%P 1-7
Markdown (Informal)
[TEDB System Description to a Shared Task on Euphemism Detection 2022](https://aclanthology.org/2022.flp-1.1) (Wiriyathammabhum, Fig-Lang 2022)
ACL