<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chi-etal-2023-learning">
    <titleInfo>
        <title>Learning to Paraphrase Sentences to Different Complexity Levels</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Alison</namePart>
        <namePart type="family">Chi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Li-Kuang</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yi-Chen</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shu-Hui</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="given">S</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>While sentence simplification is an active research topic in NLP, its adjacent tasks of sentence complexification and same-level paraphrasing are not. To train models on all three tasks, we present two new unsupervised datasets. We compare these datasets, one labeled by a weak classifier and the other by a rule-based approach, with a single supervised dataset. Using these three datasets for training, we perform extensive experiments on both multitasking and prompting strategies. Compared to other systems trained on unsupervised parallel data, models trained on our weak classifier labeled dataset achieve state-of-the-art performance on the ASSET simplification benchmark. Our models also outperform previous work on sentence-level targeting. Finally, we establish how a handful of Large Language Models perform on these tasks under a zero-shot setting.</abstract>
    <identifier type="citekey">chi-etal-2023-learning</identifier>
    <identifier type="doi">10.1162/tacl_a_00606</identifier>
    <location>
        <url>https://aclanthology.org/2023.tacl-1.76</url>
    </location>
    <part>
        <date>2023</date>
        <detail type="volume"><number>11</number></detail>
        <extent unit="page">
            <start>1332</start>
            <end>1354</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Learning to Paraphrase Sentences to Different Complexity Levels
%A Chi, Alison
%A Chen, Li-Kuang
%A Chang, Yi-Chen
%A Lee, Shu-Hui
%A Chang, Jason S.
%J Transactions of the Association for Computational Linguistics
%D 2023
%V 11
%I MIT Press
%C Cambridge, MA
%F chi-etal-2023-learning
%X While sentence simplification is an active research topic in NLP, its adjacent tasks of sentence complexification and same-level paraphrasing are not. To train models on all three tasks, we present two new unsupervised datasets. We compare these datasets, one labeled by a weak classifier and the other by a rule-based approach, with a single supervised dataset. Using these three datasets for training, we perform extensive experiments on both multitasking and prompting strategies. Compared to other systems trained on unsupervised parallel data, models trained on our weak classifier labeled dataset achieve state-of-the-art performance on the ASSET simplification benchmark. Our models also outperform previous work on sentence-level targeting. Finally, we establish how a handful of Large Language Models perform on these tasks under a zero-shot setting.
%R 10.1162/tacl_a_00606
%U https://aclanthology.org/2023.tacl-1.76
%U https://doi.org/10.1162/tacl_a_00606
%P 1332-1354

Markdown (Informal)

[Learning to Paraphrase Sentences to Different Complexity Levels](https://aclanthology.org/2023.tacl-1.76) (Chi et al., TACL 2023)

• Learning to Paraphrase Sentences to Different Complexity Levels (Chi et al., TACL 2023)

ACL

• Alison Chi, Li-Kuang Chen, Yi-Chen Chang, Shu-Hui Lee, and Jason S. Chang. 2023. Learning to Paraphrase Sentences to Different Complexity Levels. Transactions of the Association for Computational Linguistics, 11:1332–1354.