@inproceedings{robeer-etal-2021-generating-realistic,
title = "Generating Realistic Natural Language Counterfactuals",
author = "Robeer, Marcel and
Bex, Floris and
Feelders, Ad",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.306",
doi = "10.18653/v1/2021.findings-emnlp.306",
pages = "3611--3625",
abstract = "Counterfactuals are a valuable means for understanding decisions made by ML systems. However, the counterfactuals generated by the methods currently available for natural language text are either unrealistic or introduce imperceptible changes. We propose CounterfactualGAN: a method that combines a conditional GAN and the embeddings of a pretrained BERT encoder to model-agnostically generate realistic natural language text counterfactuals for explaining regression and classification tasks. Experimental results show that our method produces perceptibly distinguishable counterfactuals, while outperforming four baseline methods on fidelity and human judgments of naturalness, across multiple datasets and multiple predictive models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="robeer-etal-2021-generating-realistic">
<titleInfo>
<title>Generating Realistic Natural Language Counterfactuals</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcel</namePart>
<namePart type="family">Robeer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Floris</namePart>
<namePart type="family">Bex</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ad</namePart>
<namePart type="family">Feelders</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Counterfactuals are a valuable means for understanding decisions made by ML systems. However, the counterfactuals generated by the methods currently available for natural language text are either unrealistic or introduce imperceptible changes. We propose CounterfactualGAN: a method that combines a conditional GAN and the embeddings of a pretrained BERT encoder to model-agnostically generate realistic natural language text counterfactuals for explaining regression and classification tasks. Experimental results show that our method produces perceptibly distinguishable counterfactuals, while outperforming four baseline methods on fidelity and human judgments of naturalness, across multiple datasets and multiple predictive models.</abstract>
<identifier type="citekey">robeer-etal-2021-generating-realistic</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.306</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.306</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>3611</start>
<end>3625</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Realistic Natural Language Counterfactuals
%A Robeer, Marcel
%A Bex, Floris
%A Feelders, Ad
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F robeer-etal-2021-generating-realistic
%X Counterfactuals are a valuable means for understanding decisions made by ML systems. However, the counterfactuals generated by the methods currently available for natural language text are either unrealistic or introduce imperceptible changes. We propose CounterfactualGAN: a method that combines a conditional GAN and the embeddings of a pretrained BERT encoder to model-agnostically generate realistic natural language text counterfactuals for explaining regression and classification tasks. Experimental results show that our method produces perceptibly distinguishable counterfactuals, while outperforming four baseline methods on fidelity and human judgments of naturalness, across multiple datasets and multiple predictive models.
%R 10.18653/v1/2021.findings-emnlp.306
%U https://aclanthology.org/2021.findings-emnlp.306
%U https://doi.org/10.18653/v1/2021.findings-emnlp.306
%P 3611-3625
Markdown (Informal)
[Generating Realistic Natural Language Counterfactuals](https://aclanthology.org/2021.findings-emnlp.306) (Robeer et al., Findings 2021)
ACL
- Marcel Robeer, Floris Bex, and Ad Feelders. 2021. Generating Realistic Natural Language Counterfactuals. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3611–3625, Punta Cana, Dominican Republic. Association for Computational Linguistics.