<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-comparing-generic">
    <titleInfo>
        <title>Comparing Generic and Expert Models for Genre-Specific Text Simplification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zihao</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matthew</namePart>
        <namePart type="family">Shardlow</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fernando</namePart>
        <namePart type="family">Alva-Manchego</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 Second Workshop on Text Simplification, Accessibility and Readability</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sanja</namePart>
            <namePart type="family">Štajner</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Horacio</namePart>
            <namePart type="family">Saggio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Matthew</namePart>
            <namePart type="family">Shardlow</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Fernando</namePart>
            <namePart type="family">Alva-Manchego</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We investigate how text genre influences the performance of models for controlled text simplification. Regarding datasets from Wikipedia and PubMed as two different genres, we compare the performance of genre-specific models trained by transfer learning and prompt-only GPT-like large language models. Our experiments showed that: (1) the performance loss of genre-specific models on general tasks can be limited to 2%, (2) transfer learning can improve performance on genre-specific datasets up to 10% in SARI score from the base model without transfer learning, (3) simplifications generated by the smaller but more customized models show similar performance in simplicity and a better meaning reservation capability to the larger generic models in both automatic and human evaluations.</abstract>
    <identifier type="citekey">li-etal-2023-comparing-generic</identifier>
    <location>
        <url>https://aclanthology.org/2023.tsar-1.6</url>
    </location>
    <part>
        <date>2023-09</date>
        <extent unit="page">
            <start>51</start>
            <end>67</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Comparing Generic and Expert Models for Genre-Specific Text Simplification
%A Li, Zihao
%A Shardlow, Matthew
%A Alva-Manchego, Fernando
%Y Štajner, Sanja
%Y Saggio, Horacio
%Y Shardlow, Matthew
%Y Alva-Manchego, Fernando
%S Proceedings of the Second Workshop on Text Simplification, Accessibility and Readability
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F li-etal-2023-comparing-generic
%X We investigate how text genre influences the performance of models for controlled text simplification. Regarding datasets from Wikipedia and PubMed as two different genres, we compare the performance of genre-specific models trained by transfer learning and prompt-only GPT-like large language models. Our experiments showed that: (1) the performance loss of genre-specific models on general tasks can be limited to 2%, (2) transfer learning can improve performance on genre-specific datasets up to 10% in SARI score from the base model without transfer learning, (3) simplifications generated by the smaller but more customized models show similar performance in simplicity and a better meaning reservation capability to the larger generic models in both automatic and human evaluations.
%U https://aclanthology.org/2023.tsar-1.6
%P 51-67

Markdown (Informal)

[Comparing Generic and Expert Models for Genre-Specific Text Simplification](https://aclanthology.org/2023.tsar-1.6) (Li et al., TSAR-WS 2023)

• Comparing Generic and Expert Models for Genre-Specific Text Simplification (Li et al., TSAR-WS 2023)

ACL

• Zihao Li, Matthew Shardlow, and Fernando Alva-Manchego. 2023. Comparing Generic and Expert Models for Genre-Specific Text Simplification. In Proceedings of the Second Workshop on Text Simplification, Accessibility and Readability, pages 51–67, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.