@inproceedings{xin-etal-2021-art,
title = "The Art of Abstention: Selective Prediction and Error Regularization for Natural Language Processing",
author = "Xin, Ji and
Tang, Raphael and
Yu, Yaoliang and
Lin, Jimmy",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.84",
doi = "10.18653/v1/2021.acl-long.84",
pages = "1040--1051",
abstract = "In selective prediction, a classifier is allowed to abstain from making predictions on low-confidence examples. Though this setting is interesting and important, selective prediction has rarely been examined in natural language processing (NLP) tasks. To fill this void in the literature, we study in this paper selective prediction for NLP, comparing different models and confidence estimators. We further propose a simple error regularization trick that improves confidence estimation without substantially increasing the computation budget. We show that recent pre-trained transformer models simultaneously improve both model accuracy and confidence estimation effectiveness. We also find that our proposed regularization improves confidence estimation and can be applied to other relevant scenarios, such as using classifier cascades for accuracy{--}efficiency trade-offs. Source code for this paper can be found at \url{https://github.com/castorini/transformers-selective}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xin-etal-2021-art">
<titleInfo>
<title>The Art of Abstention: Selective Prediction and Error Regularization for Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ji</namePart>
<namePart type="family">Xin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raphael</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaoliang</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimmy</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In selective prediction, a classifier is allowed to abstain from making predictions on low-confidence examples. Though this setting is interesting and important, selective prediction has rarely been examined in natural language processing (NLP) tasks. To fill this void in the literature, we study in this paper selective prediction for NLP, comparing different models and confidence estimators. We further propose a simple error regularization trick that improves confidence estimation without substantially increasing the computation budget. We show that recent pre-trained transformer models simultaneously improve both model accuracy and confidence estimation effectiveness. We also find that our proposed regularization improves confidence estimation and can be applied to other relevant scenarios, such as using classifier cascades for accuracy–efficiency trade-offs. Source code for this paper can be found at https://github.com/castorini/transformers-selective.</abstract>
<identifier type="citekey">xin-etal-2021-art</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.84</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.84</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1040</start>
<end>1051</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Art of Abstention: Selective Prediction and Error Regularization for Natural Language Processing
%A Xin, Ji
%A Tang, Raphael
%A Yu, Yaoliang
%A Lin, Jimmy
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F xin-etal-2021-art
%X In selective prediction, a classifier is allowed to abstain from making predictions on low-confidence examples. Though this setting is interesting and important, selective prediction has rarely been examined in natural language processing (NLP) tasks. To fill this void in the literature, we study in this paper selective prediction for NLP, comparing different models and confidence estimators. We further propose a simple error regularization trick that improves confidence estimation without substantially increasing the computation budget. We show that recent pre-trained transformer models simultaneously improve both model accuracy and confidence estimation effectiveness. We also find that our proposed regularization improves confidence estimation and can be applied to other relevant scenarios, such as using classifier cascades for accuracy–efficiency trade-offs. Source code for this paper can be found at https://github.com/castorini/transformers-selective.
%R 10.18653/v1/2021.acl-long.84
%U https://aclanthology.org/2021.acl-long.84
%U https://doi.org/10.18653/v1/2021.acl-long.84
%P 1040-1051
Markdown (Informal)
[The Art of Abstention: Selective Prediction and Error Regularization for Natural Language Processing](https://aclanthology.org/2021.acl-long.84) (Xin et al., ACL-IJCNLP 2021)
ACL