@inproceedings{cauter-yakovets-2024-ontology,
title = "Ontology-guided Knowledge Graph Construction from Maintenance Short Texts",
author = "Cauter, Zeno and
Yakovets, Nikolay",
editor = "Biswas, Russa and
Kaffee, Lucie-Aim{\'e}e and
Agarwal, Oshin and
Minervini, Pasquale and
Singh, Sameer and
de Melo, Gerard",
booktitle = "Proceedings of the 1st Workshop on Knowledge Graphs and Large Language Models (KaLLM 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.kallm-1.8",
doi = "10.18653/v1/2024.kallm-1.8",
pages = "75--84",
abstract = "Large-scale knowledge graph construction remains infeasible since it requires significant human-expert involvement. Further complications arise when building graphs from domain-specific data due to their unique vocabularies and associated contexts. In this work, we demonstrate the ability of open-source large language models (LLMs), such as Llama-2 and Llama-3, to extract facts from domain-specific Maintenance Short Texts (MSTs). We employ an approach which combines ontology-guided triplet extraction and in-context learning. By using only 20 semantically similar examples with the Llama-3-70B-Instruct model, we achieve performance comparable to previous methods that relied on fine-tuning techniques like SpERT and REBEL. This indicates that domain-specific fact extraction can be accomplished through inference alone, requiring minimal labeled data. This opens up possibilities for effective and efficient semi-automated knowledge graph construction for domain-specific data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cauter-yakovets-2024-ontology">
<titleInfo>
<title>Ontology-guided Knowledge Graph Construction from Maintenance Short Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zeno</namePart>
<namePart type="family">Cauter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolay</namePart>
<namePart type="family">Yakovets</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>Large-scale knowledge graph construction remains infeasible since it requires significant human-expert involvement. Further complications arise when building graphs from domain-specific data due to their unique vocabularies and associated contexts. In this work, we demonstrate the ability of open-source large language models (LLMs), such as Llama-2 and Llama-3, to extract facts from domain-specific Maintenance Short Texts (MSTs). We employ an approach which combines ontology-guided triplet extraction and in-context learning. By using only 20 semantically similar examples with the Llama-3-70B-Instruct model, we achieve performance comparable to previous methods that relied on fine-tuning techniques like SpERT and REBEL. This indicates that domain-specific fact extraction can be accomplished through inference alone, requiring minimal labeled data. This opens up possibilities for effective and efficient semi-automated knowledge graph construction for domain-specific data.</abstract>
<identifier type="citekey">cauter-yakovets-2024-ontology</identifier>
<identifier type="doi">10.18653/v1/2024.kallm-1.8</identifier>
<location>
<url>https://aclanthology.org/2024.kallm-1.8</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>75</start>
<end>84</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ontology-guided Knowledge Graph Construction from Maintenance Short Texts
%A Cauter, Zeno
%A Yakovets, Nikolay
%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 cauter-yakovets-2024-ontology
%X Large-scale knowledge graph construction remains infeasible since it requires significant human-expert involvement. Further complications arise when building graphs from domain-specific data due to their unique vocabularies and associated contexts. In this work, we demonstrate the ability of open-source large language models (LLMs), such as Llama-2 and Llama-3, to extract facts from domain-specific Maintenance Short Texts (MSTs). We employ an approach which combines ontology-guided triplet extraction and in-context learning. By using only 20 semantically similar examples with the Llama-3-70B-Instruct model, we achieve performance comparable to previous methods that relied on fine-tuning techniques like SpERT and REBEL. This indicates that domain-specific fact extraction can be accomplished through inference alone, requiring minimal labeled data. This opens up possibilities for effective and efficient semi-automated knowledge graph construction for domain-specific data.
%R 10.18653/v1/2024.kallm-1.8
%U https://aclanthology.org/2024.kallm-1.8
%U https://doi.org/10.18653/v1/2024.kallm-1.8
%P 75-84
Markdown (Informal)
[Ontology-guided Knowledge Graph Construction from Maintenance Short Texts](https://aclanthology.org/2024.kallm-1.8) (Cauter & Yakovets, KaLLM-WS 2024)
ACL