@inproceedings{liu-etal-2022-dynamic-augmentation,
title = "Dynamic Augmentation Data Selection for Few-shot Text Classification",
author = "Liu, Guangliang and
Jin, Lifeng and
Yuan, Owen and
Zhou, Jiayu",
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.356",
doi = "10.18653/v1/2022.findings-emnlp.356",
pages = "4841--4852",
abstract = "Data augmentation has been a popular method for fine-tuning pre-trained language models to increase model robustness and performance. With augmentation data coming from modifying gold train data (in-sample augmentation) or being harvested from general domain unlabeled data (out-of-sample augmentation), the quality of such data is the key to successful fine-tuning. In this paper, we propose a dynamic data selection method to select effective augmentation data from different augmentation sources according to the model{'}s learning stage, by identifying a set of augmentation samples that optimally facilitates the learning process of the most current model. The method firstly filters out augmentation samples with noisy pseudo labels through a curriculum learning strategy, then estimates the effectiveness of reserved augmentation data by its influence scores on the current model at every update, allowing the data selection process tightly tailored to model parameters. And the two-stage augmentation strategy considers in-sample augmentation and out-of-sample augmentation in different learning stages. Experiments with both kinds of augmentation data on a variety of sentence classification tasks show that our method outperforms strong baselines, proving the effectiveness of our method. Analysis confirms the dynamic nature of the data effectiveness and the importance of model learning stages in utilization of augmentation data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2022-dynamic-augmentation">
<titleInfo>
<title>Dynamic Augmentation Data Selection for Few-shot Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guangliang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayu</namePart>
<namePart type="family">Zhou</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>Data augmentation has been a popular method for fine-tuning pre-trained language models to increase model robustness and performance. With augmentation data coming from modifying gold train data (in-sample augmentation) or being harvested from general domain unlabeled data (out-of-sample augmentation), the quality of such data is the key to successful fine-tuning. In this paper, we propose a dynamic data selection method to select effective augmentation data from different augmentation sources according to the model’s learning stage, by identifying a set of augmentation samples that optimally facilitates the learning process of the most current model. The method firstly filters out augmentation samples with noisy pseudo labels through a curriculum learning strategy, then estimates the effectiveness of reserved augmentation data by its influence scores on the current model at every update, allowing the data selection process tightly tailored to model parameters. And the two-stage augmentation strategy considers in-sample augmentation and out-of-sample augmentation in different learning stages. Experiments with both kinds of augmentation data on a variety of sentence classification tasks show that our method outperforms strong baselines, proving the effectiveness of our method. Analysis confirms the dynamic nature of the data effectiveness and the importance of model learning stages in utilization of augmentation data.</abstract>
<identifier type="citekey">liu-etal-2022-dynamic-augmentation</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.356</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.356</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>4841</start>
<end>4852</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dynamic Augmentation Data Selection for Few-shot Text Classification
%A Liu, Guangliang
%A Jin, Lifeng
%A Yuan, Owen
%A Zhou, Jiayu
%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 liu-etal-2022-dynamic-augmentation
%X Data augmentation has been a popular method for fine-tuning pre-trained language models to increase model robustness and performance. With augmentation data coming from modifying gold train data (in-sample augmentation) or being harvested from general domain unlabeled data (out-of-sample augmentation), the quality of such data is the key to successful fine-tuning. In this paper, we propose a dynamic data selection method to select effective augmentation data from different augmentation sources according to the model’s learning stage, by identifying a set of augmentation samples that optimally facilitates the learning process of the most current model. The method firstly filters out augmentation samples with noisy pseudo labels through a curriculum learning strategy, then estimates the effectiveness of reserved augmentation data by its influence scores on the current model at every update, allowing the data selection process tightly tailored to model parameters. And the two-stage augmentation strategy considers in-sample augmentation and out-of-sample augmentation in different learning stages. Experiments with both kinds of augmentation data on a variety of sentence classification tasks show that our method outperforms strong baselines, proving the effectiveness of our method. Analysis confirms the dynamic nature of the data effectiveness and the importance of model learning stages in utilization of augmentation data.
%R 10.18653/v1/2022.findings-emnlp.356
%U https://aclanthology.org/2022.findings-emnlp.356
%U https://doi.org/10.18653/v1/2022.findings-emnlp.356
%P 4841-4852
Markdown (Informal)
[Dynamic Augmentation Data Selection for Few-shot Text Classification](https://aclanthology.org/2022.findings-emnlp.356) (Liu et al., Findings 2022)
ACL