@inproceedings{wang-etal-2022-identifying,
title = "Identifying and Mitigating Spurious Correlations for Improving Robustness in {NLP} Models",
author = "Wang, Tianlu and
Sridhar, Rohit and
Yang, Diyi and
Wang, Xuezhi",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.130",
doi = "10.18653/v1/2022.findings-naacl.130",
pages = "1719--1729",
abstract = "Recently, NLP models have achieved remarkable progress across a variety of tasks; however, they have also been criticized for being not robust. Many robustness problems can be attributed to models exploiting {``}spurious correlations{''}, or {``}shortcuts{''} between the training data and the task labels. Most existing work identifies a limited set of task-specific shortcuts via human priors or error analyses, which requires extensive expertise and efforts. In this paper, we aim to automatically identify such spurious correlations in NLP models at scale. We first leverage existing interpretability methods to extract tokens that significantly affect model{'}s decision process from the input text. We then distinguish {``}genuine{''} tokens and {``}spurious{''} tokens by analyzing model predictions across multiple corpora and further verify them through knowledge-aware perturbations. We show that our proposed method can effectively and efficiently identify a scalable set of {``}shortcuts{''}, and mitigating these leads to more robust models in multiple applications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-identifying">
<titleInfo>
<title>Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianlu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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>
<name type="personal">
<namePart type="given">Xuezhi</namePart>
<namePart type="family">Wang</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>Findings of the Association for Computational Linguistics: NAACL 2022</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>Recently, NLP models have achieved remarkable progress across a variety of tasks; however, they have also been criticized for being not robust. Many robustness problems can be attributed to models exploiting “spurious correlations”, or “shortcuts” between the training data and the task labels. Most existing work identifies a limited set of task-specific shortcuts via human priors or error analyses, which requires extensive expertise and efforts. In this paper, we aim to automatically identify such spurious correlations in NLP models at scale. We first leverage existing interpretability methods to extract tokens that significantly affect model’s decision process from the input text. We then distinguish “genuine” tokens and “spurious” tokens by analyzing model predictions across multiple corpora and further verify them through knowledge-aware perturbations. We show that our proposed method can effectively and efficiently identify a scalable set of “shortcuts”, and mitigating these leads to more robust models in multiple applications.</abstract>
<identifier type="citekey">wang-etal-2022-identifying</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.130</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.130</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1719</start>
<end>1729</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models
%A Wang, Tianlu
%A Sridhar, Rohit
%A Yang, Diyi
%A Wang, Xuezhi
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F wang-etal-2022-identifying
%X Recently, NLP models have achieved remarkable progress across a variety of tasks; however, they have also been criticized for being not robust. Many robustness problems can be attributed to models exploiting “spurious correlations”, or “shortcuts” between the training data and the task labels. Most existing work identifies a limited set of task-specific shortcuts via human priors or error analyses, which requires extensive expertise and efforts. In this paper, we aim to automatically identify such spurious correlations in NLP models at scale. We first leverage existing interpretability methods to extract tokens that significantly affect model’s decision process from the input text. We then distinguish “genuine” tokens and “spurious” tokens by analyzing model predictions across multiple corpora and further verify them through knowledge-aware perturbations. We show that our proposed method can effectively and efficiently identify a scalable set of “shortcuts”, and mitigating these leads to more robust models in multiple applications.
%R 10.18653/v1/2022.findings-naacl.130
%U https://aclanthology.org/2022.findings-naacl.130
%U https://doi.org/10.18653/v1/2022.findings-naacl.130
%P 1719-1729
Markdown (Informal)
[Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models](https://aclanthology.org/2022.findings-naacl.130) (Wang et al., Findings 2022)
ACL