@inproceedings{wang-etal-2022-promda,
title = "{P}rom{DA}: Prompt-based Data Augmentation for Low-Resource {NLU} Tasks",
author = "Wang, Yufei and
Xu, Can and
Sun, Qingfeng and
Hu, Huang and
Tao, Chongyang and
Geng, Xiubo and
Jiang, Daxin",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.292",
doi = "10.18653/v1/2022.acl-long.292",
pages = "4242--4255",
abstract = "This paper focuses on the Data Augmentation for low-resource Natural Language Understanding (NLU) tasks. We propose Prompt-based Data Augmentation model (PromDA) which only trains small-scale Soft Prompt (i.e., a set of trainable vectors) in the frozen Pre-trained Language Models (PLMs). This avoids human effort in collecting unlabeled in-domain data and maintains the quality of generated synthetic data. In addition, PromDA generates synthetic data via two different views and filters out the low-quality data using NLU models. Experiments on four benchmarks show that synthetic data produced by PromDA successfully boost up the performance of NLU models which consistently outperform several competitive baseline models, including a state-of-the-art semi-supervised model using unlabeled in-domain data. The synthetic data from PromDA are also complementary with unlabeled in-domain data. The NLU models can be further improved when they are combined for training.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-promda">
<titleInfo>
<title>PromDA: Prompt-based Data Augmentation for Low-Resource NLU Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yufei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Can</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingfeng</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huang</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chongyang</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiubo</namePart>
<namePart type="family">Geng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daxin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper focuses on the Data Augmentation for low-resource Natural Language Understanding (NLU) tasks. We propose Prompt-based Data Augmentation model (PromDA) which only trains small-scale Soft Prompt (i.e., a set of trainable vectors) in the frozen Pre-trained Language Models (PLMs). This avoids human effort in collecting unlabeled in-domain data and maintains the quality of generated synthetic data. In addition, PromDA generates synthetic data via two different views and filters out the low-quality data using NLU models. Experiments on four benchmarks show that synthetic data produced by PromDA successfully boost up the performance of NLU models which consistently outperform several competitive baseline models, including a state-of-the-art semi-supervised model using unlabeled in-domain data. The synthetic data from PromDA are also complementary with unlabeled in-domain data. The NLU models can be further improved when they are combined for training.</abstract>
<identifier type="citekey">wang-etal-2022-promda</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.292</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.292</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>4242</start>
<end>4255</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PromDA: Prompt-based Data Augmentation for Low-Resource NLU Tasks
%A Wang, Yufei
%A Xu, Can
%A Sun, Qingfeng
%A Hu, Huang
%A Tao, Chongyang
%A Geng, Xiubo
%A Jiang, Daxin
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F wang-etal-2022-promda
%X This paper focuses on the Data Augmentation for low-resource Natural Language Understanding (NLU) tasks. We propose Prompt-based Data Augmentation model (PromDA) which only trains small-scale Soft Prompt (i.e., a set of trainable vectors) in the frozen Pre-trained Language Models (PLMs). This avoids human effort in collecting unlabeled in-domain data and maintains the quality of generated synthetic data. In addition, PromDA generates synthetic data via two different views and filters out the low-quality data using NLU models. Experiments on four benchmarks show that synthetic data produced by PromDA successfully boost up the performance of NLU models which consistently outperform several competitive baseline models, including a state-of-the-art semi-supervised model using unlabeled in-domain data. The synthetic data from PromDA are also complementary with unlabeled in-domain data. The NLU models can be further improved when they are combined for training.
%R 10.18653/v1/2022.acl-long.292
%U https://aclanthology.org/2022.acl-long.292
%U https://doi.org/10.18653/v1/2022.acl-long.292
%P 4242-4255
Markdown (Informal)
[PromDA: Prompt-based Data Augmentation for Low-Resource NLU Tasks](https://aclanthology.org/2022.acl-long.292) (Wang et al., ACL 2022)
ACL
- Yufei Wang, Can Xu, Qingfeng Sun, Huang Hu, Chongyang Tao, Xiubo Geng, and Daxin Jiang. 2022. PromDA: Prompt-based Data Augmentation for Low-Resource NLU Tasks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4242–4255, Dublin, Ireland. Association for Computational Linguistics.