@inproceedings{wen-etal-2022-autocad,
title = "{A}uto{CAD}: Automatically Generate Counterfactuals for Mitigating Shortcut Learning",
author = "Wen, Jiaxin and
Zhu, Yeshuang and
Zhang, Jinchao and
Zhou, Jie and
Huang, Minlie",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.170",
doi = "10.18653/v1/2022.findings-emnlp.170",
pages = "2302--2317",
abstract = "Recent studies have shown the impressive efficacy of counterfactually augmented data (CAD) for reducing NLU models{'} reliance on spurious features and improving their generalizability. However, current methods still heavily rely on human efforts or task-specific designs to generate counterfactuals, thereby impeding CAD{'}s applicability to a broad range of NLU tasks. In this paper, we present AutoCAD, a fully automatic and task-agnostic CAD generation framework. AutoCAD first leverages a classifier to unsupervisedly identify rationales as spans to be intervened, which disentangles spurious and causal features. Then, AutoCAD performs controllable generation enhanced by unlikelihood training to produce diverse counterfactuals. Extensive evaluations on multiple out-of-domain and challenge benchmarks demonstrate that AutoCAD consistently and significantly boosts the out-of-distribution performance of powerful pre-trained models across different NLU tasks, which is comparable or even better than previous state-of-the-art human-in-the-loop or task-specific CAD methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wen-etal-2022-autocad">
<titleInfo>
<title>AutoCAD: Automatically Generate Counterfactuals for Mitigating Shortcut Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeshuang</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinchao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minlie</namePart>
<namePart type="family">Huang</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>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</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</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent studies have shown the impressive efficacy of counterfactually augmented data (CAD) for reducing NLU models’ reliance on spurious features and improving their generalizability. However, current methods still heavily rely on human efforts or task-specific designs to generate counterfactuals, thereby impeding CAD’s applicability to a broad range of NLU tasks. In this paper, we present AutoCAD, a fully automatic and task-agnostic CAD generation framework. AutoCAD first leverages a classifier to unsupervisedly identify rationales as spans to be intervened, which disentangles spurious and causal features. Then, AutoCAD performs controllable generation enhanced by unlikelihood training to produce diverse counterfactuals. Extensive evaluations on multiple out-of-domain and challenge benchmarks demonstrate that AutoCAD consistently and significantly boosts the out-of-distribution performance of powerful pre-trained models across different NLU tasks, which is comparable or even better than previous state-of-the-art human-in-the-loop or task-specific CAD methods.</abstract>
<identifier type="citekey">wen-etal-2022-autocad</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.170</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.170</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>2302</start>
<end>2317</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AutoCAD: Automatically Generate Counterfactuals for Mitigating Shortcut Learning
%A Wen, Jiaxin
%A Zhu, Yeshuang
%A Zhang, Jinchao
%A Zhou, Jie
%A Huang, Minlie
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F wen-etal-2022-autocad
%X Recent studies have shown the impressive efficacy of counterfactually augmented data (CAD) for reducing NLU models’ reliance on spurious features and improving their generalizability. However, current methods still heavily rely on human efforts or task-specific designs to generate counterfactuals, thereby impeding CAD’s applicability to a broad range of NLU tasks. In this paper, we present AutoCAD, a fully automatic and task-agnostic CAD generation framework. AutoCAD first leverages a classifier to unsupervisedly identify rationales as spans to be intervened, which disentangles spurious and causal features. Then, AutoCAD performs controllable generation enhanced by unlikelihood training to produce diverse counterfactuals. Extensive evaluations on multiple out-of-domain and challenge benchmarks demonstrate that AutoCAD consistently and significantly boosts the out-of-distribution performance of powerful pre-trained models across different NLU tasks, which is comparable or even better than previous state-of-the-art human-in-the-loop or task-specific CAD methods.
%R 10.18653/v1/2022.findings-emnlp.170
%U https://aclanthology.org/2022.findings-emnlp.170
%U https://doi.org/10.18653/v1/2022.findings-emnlp.170
%P 2302-2317
Markdown (Informal)
[AutoCAD: Automatically Generate Counterfactuals for Mitigating Shortcut Learning](https://aclanthology.org/2022.findings-emnlp.170) (Wen et al., Findings 2022)
ACL