@inproceedings{sridhar-yang-2022-explaining,
title = "Explaining Toxic Text via Knowledge Enhanced Text Generation",
author = "Sridhar, Rohit and
Yang, Diyi",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.59",
doi = "10.18653/v1/2022.naacl-main.59",
pages = "811--826",
abstract = "Warning: This paper contains content that is offensive and may be upsetting. Biased or toxic speech can be harmful to various demographic groups. Therefore, it is not only important for models to detect these speech, but to also output explanations of why a given text is toxic. Previous literature has mostly focused on classifying and detecting toxic speech, and existing efforts on explaining stereotypes in toxic speech mainly use standard text generation approaches, resulting in generic and repetitive explanations. Building on these prior works, we introduce a novel knowledge-informed encoder-decoder framework to utilize multiple knowledge sources to generate implications of biased text. Experiments show that our knowledge informed models outperform prior state-of-the-art models significantly, and can generate detailed explanations of stereotypes in toxic speech compared to baselines, both quantitatively and qualitatively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sridhar-yang-2022-explaining">
<titleInfo>
<title>Explaining Toxic Text via Knowledge Enhanced Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rohit</namePart>
<namePart type="family">Sridhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</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 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</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>Warning: This paper contains content that is offensive and may be upsetting. Biased or toxic speech can be harmful to various demographic groups. Therefore, it is not only important for models to detect these speech, but to also output explanations of why a given text is toxic. Previous literature has mostly focused on classifying and detecting toxic speech, and existing efforts on explaining stereotypes in toxic speech mainly use standard text generation approaches, resulting in generic and repetitive explanations. Building on these prior works, we introduce a novel knowledge-informed encoder-decoder framework to utilize multiple knowledge sources to generate implications of biased text. Experiments show that our knowledge informed models outperform prior state-of-the-art models significantly, and can generate detailed explanations of stereotypes in toxic speech compared to baselines, both quantitatively and qualitatively.</abstract>
<identifier type="citekey">sridhar-yang-2022-explaining</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.59</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.59</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>811</start>
<end>826</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Explaining Toxic Text via Knowledge Enhanced Text Generation
%A Sridhar, Rohit
%A Yang, Diyi
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F sridhar-yang-2022-explaining
%X Warning: This paper contains content that is offensive and may be upsetting. Biased or toxic speech can be harmful to various demographic groups. Therefore, it is not only important for models to detect these speech, but to also output explanations of why a given text is toxic. Previous literature has mostly focused on classifying and detecting toxic speech, and existing efforts on explaining stereotypes in toxic speech mainly use standard text generation approaches, resulting in generic and repetitive explanations. Building on these prior works, we introduce a novel knowledge-informed encoder-decoder framework to utilize multiple knowledge sources to generate implications of biased text. Experiments show that our knowledge informed models outperform prior state-of-the-art models significantly, and can generate detailed explanations of stereotypes in toxic speech compared to baselines, both quantitatively and qualitatively.
%R 10.18653/v1/2022.naacl-main.59
%U https://aclanthology.org/2022.naacl-main.59
%U https://doi.org/10.18653/v1/2022.naacl-main.59
%P 811-826
Markdown (Informal)
[Explaining Toxic Text via Knowledge Enhanced Text Generation](https://aclanthology.org/2022.naacl-main.59) (Sridhar & Yang, NAACL 2022)
ACL
- Rohit Sridhar and Diyi Yang. 2022. Explaining Toxic Text via Knowledge Enhanced Text Generation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 811–826, Seattle, United States. Association for Computational Linguistics.