@inproceedings{wang-etal-2023-uncertainty,
title = "Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding",
author = "Wang, Jianing and
Sun, Qiushi and
Chen, Nuo and
Wang, Chengyu and
Huang, Jun and
Gao, Ming and
Li, Xiang",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.528",
doi = "10.18653/v1/2023.findings-emnlp.528",
pages = "7873--7884",
abstract = "The recent success of large pre-trained language models (PLMs) heavily hinges on massive labeled data, which typically produces inferior performance in low-resource scenarios. To remedy this dilemma, we study self-training as one of the predominant semi-supervised learning (SSL) approaches, which utilizes large-scale unlabeled data to generate synthetic examples. However, too many noisy labels will hurt the model performance, and the self-training procedure requires multiple training iterations making it more expensive if all the model parameters of the PLM are updated. This paper presents UPET, a novel Uncertainty-aware Parameter-Efficient self-Training framework to effectively and efficiently address the labeled data scarcity issue. Specifically, we incorporate Monte Carlo (MC) dropout in Bayesian neural network (BNN) to perform uncertainty estimation for the teacher model and then judiciously select reliable pseudo-labeled examples based on confidence and certainty. During the student training, we introduce multiple parameter-efficient learning (PEL) paradigms that allow optimizes only a small percentage of parameters. We also propose a novel Easy-Hard Contrastive Tuning to enhance the robustness and generalization. Extensive experiments over multiple downstream tasks demonstrate that UPET achieves a substantial improvement in terms of performance and efficiency. Our codes and data are released at https: //github.com/wjn1996/UPET.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-uncertainty">
<titleInfo>
<title>Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiushi</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The recent success of large pre-trained language models (PLMs) heavily hinges on massive labeled data, which typically produces inferior performance in low-resource scenarios. To remedy this dilemma, we study self-training as one of the predominant semi-supervised learning (SSL) approaches, which utilizes large-scale unlabeled data to generate synthetic examples. However, too many noisy labels will hurt the model performance, and the self-training procedure requires multiple training iterations making it more expensive if all the model parameters of the PLM are updated. This paper presents UPET, a novel Uncertainty-aware Parameter-Efficient self-Training framework to effectively and efficiently address the labeled data scarcity issue. Specifically, we incorporate Monte Carlo (MC) dropout in Bayesian neural network (BNN) to perform uncertainty estimation for the teacher model and then judiciously select reliable pseudo-labeled examples based on confidence and certainty. During the student training, we introduce multiple parameter-efficient learning (PEL) paradigms that allow optimizes only a small percentage of parameters. We also propose a novel Easy-Hard Contrastive Tuning to enhance the robustness and generalization. Extensive experiments over multiple downstream tasks demonstrate that UPET achieves a substantial improvement in terms of performance and efficiency. Our codes and data are released at https: //github.com/wjn1996/UPET.</abstract>
<identifier type="citekey">wang-etal-2023-uncertainty</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.528</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.528</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>7873</start>
<end>7884</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding
%A Wang, Jianing
%A Sun, Qiushi
%A Chen, Nuo
%A Wang, Chengyu
%A Huang, Jun
%A Gao, Ming
%A Li, Xiang
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F wang-etal-2023-uncertainty
%X The recent success of large pre-trained language models (PLMs) heavily hinges on massive labeled data, which typically produces inferior performance in low-resource scenarios. To remedy this dilemma, we study self-training as one of the predominant semi-supervised learning (SSL) approaches, which utilizes large-scale unlabeled data to generate synthetic examples. However, too many noisy labels will hurt the model performance, and the self-training procedure requires multiple training iterations making it more expensive if all the model parameters of the PLM are updated. This paper presents UPET, a novel Uncertainty-aware Parameter-Efficient self-Training framework to effectively and efficiently address the labeled data scarcity issue. Specifically, we incorporate Monte Carlo (MC) dropout in Bayesian neural network (BNN) to perform uncertainty estimation for the teacher model and then judiciously select reliable pseudo-labeled examples based on confidence and certainty. During the student training, we introduce multiple parameter-efficient learning (PEL) paradigms that allow optimizes only a small percentage of parameters. We also propose a novel Easy-Hard Contrastive Tuning to enhance the robustness and generalization. Extensive experiments over multiple downstream tasks demonstrate that UPET achieves a substantial improvement in terms of performance and efficiency. Our codes and data are released at https: //github.com/wjn1996/UPET.
%R 10.18653/v1/2023.findings-emnlp.528
%U https://aclanthology.org/2023.findings-emnlp.528
%U https://doi.org/10.18653/v1/2023.findings-emnlp.528
%P 7873-7884
Markdown (Informal)
[Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding](https://aclanthology.org/2023.findings-emnlp.528) (Wang et al., Findings 2023)
ACL