@inproceedings{xu-etal-2023-hard,
title = "Hard Sample Aware Prompt-Tuning",
author = "Xu, Yuanjian and
An, Qi and
Zhang, Jiahuan and
Li, Peng and
Nie, Zaiqing",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.690",
doi = "10.18653/v1/2023.acl-long.690",
pages = "12356--12369",
abstract = "Prompt-tuning based few-shot learning has garnered increasing attention in recent years due to its efficiency and promising capability. To achieve the best performance for NLP tasks with just a few samples, it is vital to include as many informative samples as possible and to avoid misleading ones. However, there is no work in prompt-tuning literature addressing the problem of differentiating informative hard samples from misleading ones in model training, which is challenging due to the lack of supervision signals about the quality of the samples to train a well-performed model. We propose a Hard Sample Aware Prompt-Tuning framework (i.e. HardPT) to solve the non-differentiable problem in hard sample identification with reinforcement learning, and to strengthen the discrimination of the feature space without changing the original data distribution via an adaptive contrastive learning method. An extensive empirical study on a series of NLP tasks demonstrates the capability of HardPT in few-shot scenarios. HardPT obtains new SOTA results on all evaluated NLP tasks, including pushing the SST-5 accuracy to 49.5{\%} (1.1{\%} point absolute improvement), QNLI accuracy to 74.6{\%} (1.9{\%} absolute improvement), NMLI accuracy to 71.5 (0.7{\%} absolute improvement), TACREV $F_1$-score to 28.2 (1.0 absolute improvement), and i2b2/VA $F_1$-score to 41.2 (1.3 absolute improvement).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2023-hard">
<titleInfo>
<title>Hard Sample Aware Prompt-Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuanjian</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaiqing</namePart>
<namePart type="family">Nie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Prompt-tuning based few-shot learning has garnered increasing attention in recent years due to its efficiency and promising capability. To achieve the best performance for NLP tasks with just a few samples, it is vital to include as many informative samples as possible and to avoid misleading ones. However, there is no work in prompt-tuning literature addressing the problem of differentiating informative hard samples from misleading ones in model training, which is challenging due to the lack of supervision signals about the quality of the samples to train a well-performed model. We propose a Hard Sample Aware Prompt-Tuning framework (i.e. HardPT) to solve the non-differentiable problem in hard sample identification with reinforcement learning, and to strengthen the discrimination of the feature space without changing the original data distribution via an adaptive contrastive learning method. An extensive empirical study on a series of NLP tasks demonstrates the capability of HardPT in few-shot scenarios. HardPT obtains new SOTA results on all evaluated NLP tasks, including pushing the SST-5 accuracy to 49.5% (1.1% point absolute improvement), QNLI accuracy to 74.6% (1.9% absolute improvement), NMLI accuracy to 71.5 (0.7% absolute improvement), TACREV F₁-score to 28.2 (1.0 absolute improvement), and i2b2/VA F₁-score to 41.2 (1.3 absolute improvement).</abstract>
<identifier type="citekey">xu-etal-2023-hard</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.690</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.690</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>12356</start>
<end>12369</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hard Sample Aware Prompt-Tuning
%A Xu, Yuanjian
%A An, Qi
%A Zhang, Jiahuan
%A Li, Peng
%A Nie, Zaiqing
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F xu-etal-2023-hard
%X Prompt-tuning based few-shot learning has garnered increasing attention in recent years due to its efficiency and promising capability. To achieve the best performance for NLP tasks with just a few samples, it is vital to include as many informative samples as possible and to avoid misleading ones. However, there is no work in prompt-tuning literature addressing the problem of differentiating informative hard samples from misleading ones in model training, which is challenging due to the lack of supervision signals about the quality of the samples to train a well-performed model. We propose a Hard Sample Aware Prompt-Tuning framework (i.e. HardPT) to solve the non-differentiable problem in hard sample identification with reinforcement learning, and to strengthen the discrimination of the feature space without changing the original data distribution via an adaptive contrastive learning method. An extensive empirical study on a series of NLP tasks demonstrates the capability of HardPT in few-shot scenarios. HardPT obtains new SOTA results on all evaluated NLP tasks, including pushing the SST-5 accuracy to 49.5% (1.1% point absolute improvement), QNLI accuracy to 74.6% (1.9% absolute improvement), NMLI accuracy to 71.5 (0.7% absolute improvement), TACREV F₁-score to 28.2 (1.0 absolute improvement), and i2b2/VA F₁-score to 41.2 (1.3 absolute improvement).
%R 10.18653/v1/2023.acl-long.690
%U https://aclanthology.org/2023.acl-long.690
%U https://doi.org/10.18653/v1/2023.acl-long.690
%P 12356-12369
Markdown (Informal)
[Hard Sample Aware Prompt-Tuning](https://aclanthology.org/2023.acl-long.690) (Xu et al., ACL 2023)
ACL
- Yuanjian Xu, Qi An, Jiahuan Zhang, Peng Li, and Zaiqing Nie. 2023. Hard Sample Aware Prompt-Tuning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12356–12369, Toronto, Canada. Association for Computational Linguistics.