<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-fine-tuning">
    <titleInfo>
        <title>Fine-tuning Language Models for Triple Extraction with Data Augmentation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yujia</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tyler</namePart>
        <namePart type="family">Sadler</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohammad</namePart>
        <namePart type="given">Reza</namePart>
        <namePart type="family">Taesiri</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenjie</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marek</namePart>
        <namePart type="family">Reformat</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 1st Workshop on Knowledge Graphs and Large Language Models (KaLLM 2024)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Russa</namePart>
            <namePart type="family">Biswas</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucie-Aimée</namePart>
            <namePart type="family">Kaffee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Oshin</namePart>
            <namePart type="family">Agarwal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Pasquale</namePart>
            <namePart type="family">Minervini</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sameer</namePart>
            <namePart type="family">Singh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gerard</namePart>
            <namePart type="family">de Melo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Advanced language models with impressive capabilities to process textual information can more effectively extract high-quality triples, which are the building blocks of knowledge graphs. Our work examines language models’ abilities to extract entities and the relationships between them. We use a diverse data augmentation process to fine-tune large language models to extract triples from the text. Fine-tuning is performed using a mix of trainers from HuggingFace and five public datasets, such as different variations of the WebNLG, SKE, DocRed, FewRel, and KELM. Evaluation involves comparing model outputs with test-set triples based on several criteria, such as type, partial, exact, and strict accuracy.The obtained results outperform ChatGPT and even match or exceed the performance of GPT-4.</abstract>
    <identifier type="citekey">zhang-etal-2024-fine-tuning</identifier>
    <identifier type="doi">10.18653/v1/2024.kallm-1.12</identifier>
    <location>
        <url>https://aclanthology.org/2024.kallm-1.12</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>116</start>
            <end>124</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Fine-tuning Language Models for Triple Extraction with Data Augmentation
%A Zhang, Yujia
%A Sadler, Tyler
%A Taesiri, Mohammad Reza
%A Xu, Wenjie
%A Reformat, Marek
%Y Biswas, Russa
%Y Kaffee, Lucie-Aimée
%Y Agarwal, Oshin
%Y Minervini, Pasquale
%Y Singh, Sameer
%Y de Melo, Gerard
%S Proceedings of the 1st Workshop on Knowledge Graphs and Large Language Models (KaLLM 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F zhang-etal-2024-fine-tuning
%X Advanced language models with impressive capabilities to process textual information can more effectively extract high-quality triples, which are the building blocks of knowledge graphs. Our work examines language models’ abilities to extract entities and the relationships between them. We use a diverse data augmentation process to fine-tune large language models to extract triples from the text. Fine-tuning is performed using a mix of trainers from HuggingFace and five public datasets, such as different variations of the WebNLG, SKE, DocRed, FewRel, and KELM. Evaluation involves comparing model outputs with test-set triples based on several criteria, such as type, partial, exact, and strict accuracy.The obtained results outperform ChatGPT and even match or exceed the performance of GPT-4.
%R 10.18653/v1/2024.kallm-1.12
%U https://aclanthology.org/2024.kallm-1.12
%U https://doi.org/10.18653/v1/2024.kallm-1.12
%P 116-124

Markdown (Informal)

[Fine-tuning Language Models for Triple Extraction with Data Augmentation](https://aclanthology.org/2024.kallm-1.12) (Zhang et al., KaLLM-WS 2024)

• Fine-tuning Language Models for Triple Extraction with Data Augmentation (Zhang et al., KaLLM-WS 2024)

ACL

• Yujia Zhang, Tyler Sadler, Mohammad Reza Taesiri, Wenjie Xu, and Marek Reformat. 2024. Fine-tuning Language Models for Triple Extraction with Data Augmentation. In Proceedings of the 1st Workshop on Knowledge Graphs and Large Language Models (KaLLM 2024), pages 116–124, Bangkok, Thailand. Association for Computational Linguistics.