<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="m-bran-etal-2024-knowledge">
    <titleInfo>
        <title>Knowledge Graph Extraction from Total Synthesis Documents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Andres</namePart>
        <namePart type="family">M Bran</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zlatko</namePart>
        <namePart type="family">Jončev</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Philippe</namePart>
        <namePart type="family">Schwaller</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 Language + Molecules (L+M 2024)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Carl</namePart>
            <namePart type="family">Edwards</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Qingyun</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Manling</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lawrence</namePart>
            <namePart type="family">Zhao</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tom</namePart>
            <namePart type="family">Hope</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Heng</namePart>
            <namePart type="family">Ji</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>Knowledge graphs (KGs) have emerged as a powerful tool for organizing and integrating complex information, making it a suitable format for scientific knowledge. However, translating scientific knowledge into KGs is challenging as a wide variety of styles and elements to present data and ideas is used. Although efforts for KG extraction (KGE) from scientific documents exist, evaluation remains challenging and field-dependent; and existing benchmarks do not focuse on scientific information. Furthermore, establishing a general benchmark for this task is challenging as not all scientific knowledge has a ground-truth KG representation, making any benchmark prone to ambiguity. Here we propose Graph of Organic Synthesis Benchmark (GOSyBench), a benchmark for KG extraction from scientific documents in chemistry, that leverages the native KG-like structure of synthetic routes in organic chemistry. We develop KG-extraction algorithms based on LLMs (GPT-4, Claude, Mistral) and VLMs (GPT-4o), the best of which reaches 73% recovery accuracy and 59% precision, leaving a lot of room for improvement. We expect GOSyBench can serve as a valuable resource for evaluating and advancing KGE methods in the scientific domain, ultimately facilitating better organization, integration, and discovery of scientific knowledge.</abstract>
    <identifier type="citekey">m-bran-etal-2024-knowledge</identifier>
    <location>
        <url>https://aclanthology.org/2024.langmol-1.9</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>74</start>
            <end>84</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Knowledge Graph Extraction from Total Synthesis Documents
%A M Bran, Andres
%A Jončev, Zlatko
%A Schwaller, Philippe
%Y Edwards, Carl
%Y Wang, Qingyun
%Y Li, Manling
%Y Zhao, Lawrence
%Y Hope, Tom
%Y Ji, Heng
%S Proceedings of the 1st Workshop on Language + Molecules (L+M 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F m-bran-etal-2024-knowledge
%X Knowledge graphs (KGs) have emerged as a powerful tool for organizing and integrating complex information, making it a suitable format for scientific knowledge. However, translating scientific knowledge into KGs is challenging as a wide variety of styles and elements to present data and ideas is used. Although efforts for KG extraction (KGE) from scientific documents exist, evaluation remains challenging and field-dependent; and existing benchmarks do not focuse on scientific information. Furthermore, establishing a general benchmark for this task is challenging as not all scientific knowledge has a ground-truth KG representation, making any benchmark prone to ambiguity. Here we propose Graph of Organic Synthesis Benchmark (GOSyBench), a benchmark for KG extraction from scientific documents in chemistry, that leverages the native KG-like structure of synthetic routes in organic chemistry. We develop KG-extraction algorithms based on LLMs (GPT-4, Claude, Mistral) and VLMs (GPT-4o), the best of which reaches 73% recovery accuracy and 59% precision, leaving a lot of room for improvement. We expect GOSyBench can serve as a valuable resource for evaluating and advancing KGE methods in the scientific domain, ultimately facilitating better organization, integration, and discovery of scientific knowledge.
%U https://aclanthology.org/2024.langmol-1.9
%P 74-84

Markdown (Informal)

[Knowledge Graph Extraction from Total Synthesis Documents](https://aclanthology.org/2024.langmol-1.9) (M Bran et al., LangMol-WS 2024)

• Knowledge Graph Extraction from Total Synthesis Documents (M Bran et al., LangMol-WS 2024)

ACL

• Andres M Bran, Zlatko Jončev, and Philippe Schwaller. 2024. Knowledge Graph Extraction from Total Synthesis Documents. In Proceedings of the 1st Workshop on Language + Molecules (L+M 2024), pages 74–84, Bangkok, Thailand. Association for Computational Linguistics.