@inproceedings{yu-etal-2022-actune,
title = "{A}c{T}une: Uncertainty-Based Active Self-Training for Active Fine-Tuning of Pretrained Language Models",
author = "Yu, Yue and
Kong, Lingkai and
Zhang, Jieyu and
Zhang, Rongzhi and
Zhang, Chao",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.102",
doi = "10.18653/v1/2022.naacl-main.102",
pages = "1422--1436",
abstract = "Although fine-tuning pre-trained language models (PLMs) renders strong performance in many NLP tasks, it relies on excessive labeled data. Recently, researchers have resorted to active fine-tuning for enhancing the label efficiency of PLM fine-tuning, but existing methods of this type usually ignore the potential of unlabeled data. We develop AcTune, a new framework that improves the label efficiency of active PLM fine-tuning by unleashing the power of unlabeled data via self-training. AcTune switches between data annotation and model self-training based on uncertainty: the unlabeled samples of high-uncertainty are selected for annotation, while the ones from low-uncertainty regions are used for model self-training. Additionally, we design (1) a region-aware sampling strategy to avoid redundant samples when querying annotations and (2) a momentum-based memory bank to dynamically aggregate the model{'}s pseudo labels to suppress label noise in self-training. Experiments on 6 text classification datasets show that AcTune outperforms the strongest active learning and self-training baselines and improves the label efficiency of PLM fine-tuning by 56.2{\%} on average. Our implementation is available at \url{https://github.com/yueyu1030/actune}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2022-actune">
<titleInfo>
<title>AcTune: Uncertainty-Based Active Self-Training for Active Fine-Tuning of Pretrained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingkai</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rongzhi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Zhang</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>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</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>Although fine-tuning pre-trained language models (PLMs) renders strong performance in many NLP tasks, it relies on excessive labeled data. Recently, researchers have resorted to active fine-tuning for enhancing the label efficiency of PLM fine-tuning, but existing methods of this type usually ignore the potential of unlabeled data. We develop AcTune, a new framework that improves the label efficiency of active PLM fine-tuning by unleashing the power of unlabeled data via self-training. AcTune switches between data annotation and model self-training based on uncertainty: the unlabeled samples of high-uncertainty are selected for annotation, while the ones from low-uncertainty regions are used for model self-training. Additionally, we design (1) a region-aware sampling strategy to avoid redundant samples when querying annotations and (2) a momentum-based memory bank to dynamically aggregate the model’s pseudo labels to suppress label noise in self-training. Experiments on 6 text classification datasets show that AcTune outperforms the strongest active learning and self-training baselines and improves the label efficiency of PLM fine-tuning by 56.2% on average. Our implementation is available at https://github.com/yueyu1030/actune.</abstract>
<identifier type="citekey">yu-etal-2022-actune</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.102</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.102</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1422</start>
<end>1436</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AcTune: Uncertainty-Based Active Self-Training for Active Fine-Tuning of Pretrained Language Models
%A Yu, Yue
%A Kong, Lingkai
%A Zhang, Jieyu
%A Zhang, Rongzhi
%A Zhang, Chao
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F yu-etal-2022-actune
%X Although fine-tuning pre-trained language models (PLMs) renders strong performance in many NLP tasks, it relies on excessive labeled data. Recently, researchers have resorted to active fine-tuning for enhancing the label efficiency of PLM fine-tuning, but existing methods of this type usually ignore the potential of unlabeled data. We develop AcTune, a new framework that improves the label efficiency of active PLM fine-tuning by unleashing the power of unlabeled data via self-training. AcTune switches between data annotation and model self-training based on uncertainty: the unlabeled samples of high-uncertainty are selected for annotation, while the ones from low-uncertainty regions are used for model self-training. Additionally, we design (1) a region-aware sampling strategy to avoid redundant samples when querying annotations and (2) a momentum-based memory bank to dynamically aggregate the model’s pseudo labels to suppress label noise in self-training. Experiments on 6 text classification datasets show that AcTune outperforms the strongest active learning and self-training baselines and improves the label efficiency of PLM fine-tuning by 56.2% on average. Our implementation is available at https://github.com/yueyu1030/actune.
%R 10.18653/v1/2022.naacl-main.102
%U https://aclanthology.org/2022.naacl-main.102
%U https://doi.org/10.18653/v1/2022.naacl-main.102
%P 1422-1436
Markdown (Informal)
[AcTune: Uncertainty-Based Active Self-Training for Active Fine-Tuning of Pretrained Language Models](https://aclanthology.org/2022.naacl-main.102) (Yu et al., NAACL 2022)
ACL