@inproceedings{perez-almendros-schockaert-2022-identifying,
title = "Identifying Condescending Language: A Tale of Two Distinct Phenomena?",
author = "Perez Almendros, Carla and
Schockaert, Steven",
editor = "Biester, Laura and
Demszky, Dorottya and
Jin, Zhijing and
Sachan, Mrinmaya and
Tetreault, Joel and
Wilson, Steven and
Xiao, Lu and
Zhao, Jieyu",
booktitle = "Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.nlp4pi-1.15",
doi = "10.18653/v1/2022.nlp4pi-1.15",
pages = "130--141",
abstract = "Patronizing and condescending language is characterized, among others, by its subtle nature. It thus seems reasonable to assume that detecting condescending language in text would be harder than detecting more explicitly harmful language, such as hate speech. However, the results of a SemEval-2022 Task devoted to this topic paint a different picture, with the top-performing systems achieving remarkably strong results. In this paper, we analyse the surprising effectiveness of standard text classification methods in more detail. In particular, we highlight the presence of two rather different types of condescending language in the dataset from the SemEval task. Some inputs are condescending because of the way they talk about a particular subject, i.e. condescending language in this case is a linguistic phenomenon, which can, in principle, be learned from training examples. However, other inputs are condescending because of the nature of what is said, rather than the way in which it is expressed, e.g. by emphasizing stereotypes about a given community. In such cases, our ability to detect condescending language, with current methods, largely depends on the presence of similar examples in the training data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="perez-almendros-schockaert-2022-identifying">
<titleInfo>
<title>Identifying Condescending Language: A Tale of Two Distinct Phenomena?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="family">Perez Almendros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</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 Second Workshop on NLP for Positive Impact (NLP4PI)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Biester</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dorottya</namePart>
<namePart type="family">Demszky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhijing</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mrinmaya</namePart>
<namePart type="family">Sachan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Wilson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhao</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>Patronizing and condescending language is characterized, among others, by its subtle nature. It thus seems reasonable to assume that detecting condescending language in text would be harder than detecting more explicitly harmful language, such as hate speech. However, the results of a SemEval-2022 Task devoted to this topic paint a different picture, with the top-performing systems achieving remarkably strong results. In this paper, we analyse the surprising effectiveness of standard text classification methods in more detail. In particular, we highlight the presence of two rather different types of condescending language in the dataset from the SemEval task. Some inputs are condescending because of the way they talk about a particular subject, i.e. condescending language in this case is a linguistic phenomenon, which can, in principle, be learned from training examples. However, other inputs are condescending because of the nature of what is said, rather than the way in which it is expressed, e.g. by emphasizing stereotypes about a given community. In such cases, our ability to detect condescending language, with current methods, largely depends on the presence of similar examples in the training data.</abstract>
<identifier type="citekey">perez-almendros-schockaert-2022-identifying</identifier>
<identifier type="doi">10.18653/v1/2022.nlp4pi-1.15</identifier>
<location>
<url>https://aclanthology.org/2022.nlp4pi-1.15</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>130</start>
<end>141</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Condescending Language: A Tale of Two Distinct Phenomena?
%A Perez Almendros, Carla
%A Schockaert, Steven
%Y Biester, Laura
%Y Demszky, Dorottya
%Y Jin, Zhijing
%Y Sachan, Mrinmaya
%Y Tetreault, Joel
%Y Wilson, Steven
%Y Xiao, Lu
%Y Zhao, Jieyu
%S Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F perez-almendros-schockaert-2022-identifying
%X Patronizing and condescending language is characterized, among others, by its subtle nature. It thus seems reasonable to assume that detecting condescending language in text would be harder than detecting more explicitly harmful language, such as hate speech. However, the results of a SemEval-2022 Task devoted to this topic paint a different picture, with the top-performing systems achieving remarkably strong results. In this paper, we analyse the surprising effectiveness of standard text classification methods in more detail. In particular, we highlight the presence of two rather different types of condescending language in the dataset from the SemEval task. Some inputs are condescending because of the way they talk about a particular subject, i.e. condescending language in this case is a linguistic phenomenon, which can, in principle, be learned from training examples. However, other inputs are condescending because of the nature of what is said, rather than the way in which it is expressed, e.g. by emphasizing stereotypes about a given community. In such cases, our ability to detect condescending language, with current methods, largely depends on the presence of similar examples in the training data.
%R 10.18653/v1/2022.nlp4pi-1.15
%U https://aclanthology.org/2022.nlp4pi-1.15
%U https://doi.org/10.18653/v1/2022.nlp4pi-1.15
%P 130-141
Markdown (Informal)
[Identifying Condescending Language: A Tale of Two Distinct Phenomena?](https://aclanthology.org/2022.nlp4pi-1.15) (Perez Almendros & Schockaert, NLP4PI 2022)
ACL