@inproceedings{m-bran-etal-2024-knowledge,
title = "Knowledge Graph Extraction from Total Synthesis Documents",
author = "M Bran, Andres and
Jon{\v{c}}ev, Zlatko and
Schwaller, Philippe",
editor = "Edwards, Carl and
Wang, Qingyun and
Li, Manling and
Zhao, Lawrence and
Hope, Tom and
Ji, Heng",
booktitle = "Proceedings of the 1st Workshop on Language + Molecules (L+M 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.langmol-1.9",
pages = "74--84",
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.",
}
<?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)
ACL