<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="osuji-etal-2024-pipeline-neural">
    <titleInfo>
        <title>Pipeline Neural Data-to-text with Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chinonso</namePart>
        <namePart type="given">Cynthia</namePart>
        <namePart type="family">Osuji</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Brian</namePart>
        <namePart type="family">Timoney</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Thiago</namePart>
        <namePart type="family">Castro Ferreira</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Brian</namePart>
        <namePart type="family">Davis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th International Natural Language Generation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Saad</namePart>
            <namePart type="family">Mahamood</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nguyen</namePart>
            <namePart type="given">Le</namePart>
            <namePart type="family">Minh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Daphne</namePart>
            <namePart type="family">Ippolito</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Tokyo, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Previous studies have highlighted the advantages of pipeline neural architectures over end-to-end models, particularly in reducing text hallucination. In this study, we extend prior research by integrating pretrained language models (PLMs) into a pipeline framework, using both fine-tuning and prompting methods. Our findings show that fine-tuned PLMs consistently generate high quality text, especially within end-to-end architectures and at intermediate stages of the pipeline across various domains. These models also outperform prompt-based ones on automatic evaluation metrics but lag in human evaluations. Compared to the standard five-stage pipeline architecture, a streamlined three-stage pipeline, which only include ordering, structuring, and surface realization, achieves superior performance in fluency and semantic adequacy according to the human evaluation.</abstract>
    <identifier type="citekey">osuji-etal-2024-pipeline-neural</identifier>
    <location>
        <url>https://aclanthology.org/2024.inlg-main.27</url>
    </location>
    <part>
        <date>2024-09</date>
        <extent unit="page">
            <start>320</start>
            <end>329</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Pipeline Neural Data-to-text with Large Language Models
%A Osuji, Chinonso Cynthia
%A Timoney, Brian
%A Castro Ferreira, Thiago
%A Davis, Brian
%Y Mahamood, Saad
%Y Minh, Nguyen Le
%Y Ippolito, Daphne
%S Proceedings of the 17th International Natural Language Generation Conference
%D 2024
%8 September
%I Association for Computational Linguistics
%C Tokyo, Japan
%F osuji-etal-2024-pipeline-neural
%X Previous studies have highlighted the advantages of pipeline neural architectures over end-to-end models, particularly in reducing text hallucination. In this study, we extend prior research by integrating pretrained language models (PLMs) into a pipeline framework, using both fine-tuning and prompting methods. Our findings show that fine-tuned PLMs consistently generate high quality text, especially within end-to-end architectures and at intermediate stages of the pipeline across various domains. These models also outperform prompt-based ones on automatic evaluation metrics but lag in human evaluations. Compared to the standard five-stage pipeline architecture, a streamlined three-stage pipeline, which only include ordering, structuring, and surface realization, achieves superior performance in fluency and semantic adequacy according to the human evaluation.
%U https://aclanthology.org/2024.inlg-main.27
%P 320-329

Markdown (Informal)

[Pipeline Neural Data-to-text with Large Language Models](https://aclanthology.org/2024.inlg-main.27) (Osuji et al., INLG 2024)

• Pipeline Neural Data-to-text with Large Language Models (Osuji et al., INLG 2024)

ACL

• Chinonso Cynthia Osuji, Brian Timoney, Thiago Castro Ferreira, and Brian Davis. 2024. Pipeline Neural Data-to-text with Large Language Models. In Proceedings of the 17th International Natural Language Generation Conference, pages 320–329, Tokyo, Japan. Association for Computational Linguistics.