<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mukherjee-dusek-2023-leveraging">
    <titleInfo>
        <title>Leveraging Low-resource Parallel Data for Text Style Transfer</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sourabrata</namePart>
        <namePart type="family">Mukherjee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ondrej</namePart>
        <namePart type="family">Dusek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 16th International Natural Language Generation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">C</namePart>
            <namePart type="given">Maria</namePart>
            <namePart type="family">Keet</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sina</namePart>
            <namePart type="family">Zarrieß</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Prague, Czechia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Text style transfer (TST) involves transforming a text into a desired style while approximately preserving its content. The biggest challenge in TST in the general lack of parallel data. Many existing approaches rely on complex models using substantial non-parallel data, with mixed results. In this paper, we leverage a pretrained BART language model with minimal parallel data and incorporate low-resource methods such as hyperparameter tuning, data augmentation, and self-training, which have not been explored in TST. We further include novel style-based rewards in the training loss. Through extensive experiments in sentiment transfer, a sub-task of TST, we demonstrate that our simple yet effective approaches achieve well-balanced results, surpassing non-parallel approaches and highlighting the usefulness of parallel data even in small amounts.</abstract>
    <identifier type="citekey">mukherjee-dusek-2023-leveraging</identifier>
    <identifier type="doi">10.18653/v1/2023.inlg-main.27</identifier>
    <location>
        <url>https://aclanthology.org/2023.inlg-main.27</url>
    </location>
    <part>
        <date>2023-09</date>
        <extent unit="page">
            <start>388</start>
            <end>395</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Leveraging Low-resource Parallel Data for Text Style Transfer
%A Mukherjee, Sourabrata
%A Dusek, Ondrej
%Y Keet, C. Maria
%Y Lee, Hung-Yi
%Y Zarrieß, Sina
%S Proceedings of the 16th International Natural Language Generation Conference
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czechia
%F mukherjee-dusek-2023-leveraging
%X Text style transfer (TST) involves transforming a text into a desired style while approximately preserving its content. The biggest challenge in TST in the general lack of parallel data. Many existing approaches rely on complex models using substantial non-parallel data, with mixed results. In this paper, we leverage a pretrained BART language model with minimal parallel data and incorporate low-resource methods such as hyperparameter tuning, data augmentation, and self-training, which have not been explored in TST. We further include novel style-based rewards in the training loss. Through extensive experiments in sentiment transfer, a sub-task of TST, we demonstrate that our simple yet effective approaches achieve well-balanced results, surpassing non-parallel approaches and highlighting the usefulness of parallel data even in small amounts.
%R 10.18653/v1/2023.inlg-main.27
%U https://aclanthology.org/2023.inlg-main.27
%U https://doi.org/10.18653/v1/2023.inlg-main.27
%P 388-395

Markdown (Informal)

[Leveraging Low-resource Parallel Data for Text Style Transfer](https://aclanthology.org/2023.inlg-main.27) (Mukherjee & Dusek, INLG-SIGDIAL 2023)

• Leveraging Low-resource Parallel Data for Text Style Transfer (Mukherjee & Dusek, INLG-SIGDIAL 2023)

ACL

• Sourabrata Mukherjee and Ondrej Dusek. 2023. Leveraging Low-resource Parallel Data for Text Style Transfer. In Proceedings of the 16th International Natural Language Generation Conference, pages 388–395, Prague, Czechia. Association for Computational Linguistics.