<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2023-simple">
    <titleInfo>
        <title>A Simple Yet Strong Domain-Agnostic De-bias Method for Zero-Shot Sentiment Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tetsuya</namePart>
        <namePart type="family">Nasukawa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Masayasu</namePart>
        <namePart type="family">Muraoka</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bishwaranjan</namePart>
        <namePart type="family">Bhattacharjee</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>Findings of the Association for Computational Linguistics: ACL 2023</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>Zero-shot prompt-based learning has made much progress in sentiment analysis, and considerable effort has been dedicated to designing high-performing prompt templates. However, two problems exist; First, large language models are often biased to their pre-training data, leading to poor performance in prompt templates that models have rarely seen. Second, in order to adapt to different domains, re-designing prompt templates is usually required, which is time-consuming and inefficient. To remedy both shortcomings, we propose a simple yet strong data construction method to de-bias a given prompt template, yielding a large performance improvement in sentiment analysis tasks across different domains, pre-trained language models, and prompt templates. Also, we demonstrate the advantage of using domain-agnostic generic responses over the in-domain ground-truth data.</abstract>
    <identifier type="citekey">zhao-etal-2023-simple</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.242</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.242</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>3923</start>
            <end>3931</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Simple Yet Strong Domain-Agnostic De-bias Method for Zero-Shot Sentiment Classification
%A Zhao, Yang
%A Nasukawa, Tetsuya
%A Muraoka, Masayasu
%A Bhattacharjee, Bishwaranjan
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F zhao-etal-2023-simple
%X Zero-shot prompt-based learning has made much progress in sentiment analysis, and considerable effort has been dedicated to designing high-performing prompt templates. However, two problems exist; First, large language models are often biased to their pre-training data, leading to poor performance in prompt templates that models have rarely seen. Second, in order to adapt to different domains, re-designing prompt templates is usually required, which is time-consuming and inefficient. To remedy both shortcomings, we propose a simple yet strong data construction method to de-bias a given prompt template, yielding a large performance improvement in sentiment analysis tasks across different domains, pre-trained language models, and prompt templates. Also, we demonstrate the advantage of using domain-agnostic generic responses over the in-domain ground-truth data.
%R 10.18653/v1/2023.findings-acl.242
%U https://aclanthology.org/2023.findings-acl.242
%U https://doi.org/10.18653/v1/2023.findings-acl.242
%P 3923-3931

Markdown (Informal)

[A Simple Yet Strong Domain-Agnostic De-bias Method for Zero-Shot Sentiment Classification](https://aclanthology.org/2023.findings-acl.242) (Zhao et al., Findings 2023)

• A Simple Yet Strong Domain-Agnostic De-bias Method for Zero-Shot Sentiment Classification (Zhao et al., Findings 2023)

ACL

• Yang Zhao, Tetsuya Nasukawa, Masayasu Muraoka, and Bishwaranjan Bhattacharjee. 2023. A Simple Yet Strong Domain-Agnostic De-bias Method for Zero-Shot Sentiment Classification. In Findings of the Association for Computational Linguistics: ACL 2023, pages 3923–3931, Toronto, Canada. Association for Computational Linguistics.