@inproceedings{bestgen-2022-satlab,
title = "{SATL}ab at {S}em{E}val-2022 Task 4: Trying to Detect Patronizing and Condescending Language with only Character and Word N-grams",
author = "Bestgen, Yves",
editor = "Emerson, Guy and
Schluter, Natalie and
Stanovsky, Gabriel and
Kumar, Ritesh and
Palmer, Alexis and
Schneider, Nathan and
Singh, Siddharth and
Ratan, Shyam",
booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.semeval-1.67/",
doi = "10.18653/v1/2022.semeval-1.67",
pages = "490--495",
abstract = "A logistic regression model only fed with character and word n-grams is proposed for the SemEval-2022 Task 4 on Patronizing and Condescending Language Detection (PCL). It obtained an average level of performance, well above the performance of a system that tries to guess without using any knowledge about the task, but much lower than the best teams. To facilitate the interpretation of the performance scores, the F1 measure, the best level of performance of a system that tries to guess without using any knowledge is calculated and used to correct the F1 scores in the manner of a Kappa. As the proposed model is very similar to the one that performed well on a task requiring to automatically identify hate speech and offensive content, this paper confirms the difficulty of PCL detection."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bestgen-2022-satlab">
<titleInfo>
<title>SATLab at SemEval-2022 Task 4: Trying to Detect Patronizing and Condescending Language with only Character and Word N-grams</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Bestgen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyam</namePart>
<namePart type="family">Ratan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A logistic regression model only fed with character and word n-grams is proposed for the SemEval-2022 Task 4 on Patronizing and Condescending Language Detection (PCL). It obtained an average level of performance, well above the performance of a system that tries to guess without using any knowledge about the task, but much lower than the best teams. To facilitate the interpretation of the performance scores, the F1 measure, the best level of performance of a system that tries to guess without using any knowledge is calculated and used to correct the F1 scores in the manner of a Kappa. As the proposed model is very similar to the one that performed well on a task requiring to automatically identify hate speech and offensive content, this paper confirms the difficulty of PCL detection.</abstract>
<identifier type="citekey">bestgen-2022-satlab</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.67</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.67/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>490</start>
<end>495</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SATLab at SemEval-2022 Task 4: Trying to Detect Patronizing and Condescending Language with only Character and Word N-grams
%A Bestgen, Yves
%Y Emerson, Guy
%Y Schluter, Natalie
%Y Stanovsky, Gabriel
%Y Kumar, Ritesh
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Singh, Siddharth
%Y Ratan, Shyam
%S Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F bestgen-2022-satlab
%X A logistic regression model only fed with character and word n-grams is proposed for the SemEval-2022 Task 4 on Patronizing and Condescending Language Detection (PCL). It obtained an average level of performance, well above the performance of a system that tries to guess without using any knowledge about the task, but much lower than the best teams. To facilitate the interpretation of the performance scores, the F1 measure, the best level of performance of a system that tries to guess without using any knowledge is calculated and used to correct the F1 scores in the manner of a Kappa. As the proposed model is very similar to the one that performed well on a task requiring to automatically identify hate speech and offensive content, this paper confirms the difficulty of PCL detection.
%R 10.18653/v1/2022.semeval-1.67
%U https://aclanthology.org/2022.semeval-1.67/
%U https://doi.org/10.18653/v1/2022.semeval-1.67
%P 490-495
Markdown (Informal)
[SATLab at SemEval-2022 Task 4: Trying to Detect Patronizing and Condescending Language with only Character and Word N-grams](https://aclanthology.org/2022.semeval-1.67/) (Bestgen, SemEval 2022)
ACL