<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-lee-2023-prompt">
    <titleInfo>
        <title>Prompt-based Learning for Text Readability Assessment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bruce</namePart>
        <namePart type="given">W</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jason</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabelle</namePart>
            <namePart type="family">Augenstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dubrovnik, Croatia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We propose the novel adaptation of a pre-trained seq2seq model for readability assessment. We prove that a seq2seq model - T5 or BART - can be adapted to discern which text is more difficult from two given texts (pairwise). As an exploratory study to prompt-learn a neural network for text readability in a text-to-text manner, we report useful tips for future work in seq2seq training and ranking-based approach to readability assessment. Specifically, we test nine input-output formats/prefixes and show that they can significantly influence the final model performance. Also, we argue that the combination of text-to-text training and pairwise ranking setup 1) enables leveraging multiple parallel text simplification data for teaching readability and 2) trains a neural model for the general concept of readability (therefore, better cross-domain generalization). At last, we report a 99.6% pairwise classification accuracy on Newsela and a 98.7% for OneStopEnglish, through a joint training approach. Our code is available at github.com/brucewlee/prompt-learning-readability.</abstract>
    <identifier type="citekey">lee-lee-2023-prompt</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-eacl.135</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-eacl.135</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>1819</start>
            <end>1824</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Prompt-based Learning for Text Readability Assessment
%A Lee, Bruce W.
%A Lee, Jason
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F lee-lee-2023-prompt
%X We propose the novel adaptation of a pre-trained seq2seq model for readability assessment. We prove that a seq2seq model - T5 or BART - can be adapted to discern which text is more difficult from two given texts (pairwise). As an exploratory study to prompt-learn a neural network for text readability in a text-to-text manner, we report useful tips for future work in seq2seq training and ranking-based approach to readability assessment. Specifically, we test nine input-output formats/prefixes and show that they can significantly influence the final model performance. Also, we argue that the combination of text-to-text training and pairwise ranking setup 1) enables leveraging multiple parallel text simplification data for teaching readability and 2) trains a neural model for the general concept of readability (therefore, better cross-domain generalization). At last, we report a 99.6% pairwise classification accuracy on Newsela and a 98.7% for OneStopEnglish, through a joint training approach. Our code is available at github.com/brucewlee/prompt-learning-readability.
%R 10.18653/v1/2023.findings-eacl.135
%U https://aclanthology.org/2023.findings-eacl.135
%U https://doi.org/10.18653/v1/2023.findings-eacl.135
%P 1819-1824

Markdown (Informal)

[Prompt-based Learning for Text Readability Assessment](https://aclanthology.org/2023.findings-eacl.135) (Lee & Lee, Findings 2023)

• Prompt-based Learning for Text Readability Assessment (Lee & Lee, Findings 2023)

ACL

• Bruce W. Lee and Jason Lee. 2023. Prompt-based Learning for Text Readability Assessment. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1819–1824, Dubrovnik, Croatia. Association for Computational Linguistics.