@inproceedings{wu-shi-2022-adversarial,
title = "Adversarial Soft Prompt Tuning for Cross-Domain Sentiment Analysis",
author = "Wu, Hui and
Shi, Xiaodong",
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.174",
doi = "10.18653/v1/2022.acl-long.174",
pages = "2438--2447",
abstract = "Cross-domain sentiment analysis has achieved promising results with the help of pre-trained language models. As GPT-3 appears, prompt tuning has been widely explored to enable better semantic modeling in many natural language processing tasks. However, directly using a fixed predefined template for cross-domain research cannot model different distributions of the $\operatorname{[MASK]}$ token in different domains, thus making underuse of the prompt tuning technique. In this paper, we propose a novel \textbf{Ad}versarial \textbf{S}oft \textbf{P}rompt \textbf{T}uning method (AdSPT) to better model cross-domain sentiment analysis. On the one hand, AdSPT adopts separate soft prompts instead of hard templates to learn different vectors for different domains, thus alleviating the domain discrepancy of the $\operatorname{[MASK]}$ token in the masked language modeling task. On the other hand, AdSPT uses a novel domain adversarial training strategy to learn domain-invariant representations between each source domain and the target domain. Experiments on a publicly available sentiment analysis dataset show that our model achieves the new state-of-the-art results for both single-source domain adaptation and multi-source domain adaptation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-shi-2022-adversarial">
<titleInfo>
<title>Adversarial Soft Prompt Tuning for Cross-Domain Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodong</namePart>
<namePart type="family">Shi</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>Cross-domain sentiment analysis has achieved promising results with the help of pre-trained language models. As GPT-3 appears, prompt tuning has been widely explored to enable better semantic modeling in many natural language processing tasks. However, directly using a fixed predefined template for cross-domain research cannot model different distributions of the øperatorname[MASK] token in different domains, thus making underuse of the prompt tuning technique. In this paper, we propose a novel Adversarial Soft Prompt Tuning method (AdSPT) to better model cross-domain sentiment analysis. On the one hand, AdSPT adopts separate soft prompts instead of hard templates to learn different vectors for different domains, thus alleviating the domain discrepancy of the øperatorname[MASK] token in the masked language modeling task. On the other hand, AdSPT uses a novel domain adversarial training strategy to learn domain-invariant representations between each source domain and the target domain. Experiments on a publicly available sentiment analysis dataset show that our model achieves the new state-of-the-art results for both single-source domain adaptation and multi-source domain adaptation.</abstract>
<identifier type="citekey">wu-shi-2022-adversarial</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.174</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.174</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>2438</start>
<end>2447</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adversarial Soft Prompt Tuning for Cross-Domain Sentiment Analysis
%A Wu, Hui
%A Shi, Xiaodong
%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 wu-shi-2022-adversarial
%X Cross-domain sentiment analysis has achieved promising results with the help of pre-trained language models. As GPT-3 appears, prompt tuning has been widely explored to enable better semantic modeling in many natural language processing tasks. However, directly using a fixed predefined template for cross-domain research cannot model different distributions of the øperatorname[MASK] token in different domains, thus making underuse of the prompt tuning technique. In this paper, we propose a novel Adversarial Soft Prompt Tuning method (AdSPT) to better model cross-domain sentiment analysis. On the one hand, AdSPT adopts separate soft prompts instead of hard templates to learn different vectors for different domains, thus alleviating the domain discrepancy of the øperatorname[MASK] token in the masked language modeling task. On the other hand, AdSPT uses a novel domain adversarial training strategy to learn domain-invariant representations between each source domain and the target domain. Experiments on a publicly available sentiment analysis dataset show that our model achieves the new state-of-the-art results for both single-source domain adaptation and multi-source domain adaptation.
%R 10.18653/v1/2022.acl-long.174
%U https://aclanthology.org/2022.acl-long.174
%U https://doi.org/10.18653/v1/2022.acl-long.174
%P 2438-2447
Markdown (Informal)
[Adversarial Soft Prompt Tuning for Cross-Domain Sentiment Analysis](https://aclanthology.org/2022.acl-long.174) (Wu & Shi, ACL 2022)
ACL