iText2KG: Incremental Knowledge Graphs Construction Using Large Language Models - Archive ouverte HAL
Conference Papers Year : 2024

iText2KG: Incremental Knowledge Graphs Construction Using Large Language Models

Abstract

Most available data is unstructured, making it challenging to access valuable information. Automatically building Knowledge Graphs (KGs) is crucial for structuring data and making it accessible, allowing users to search for information effectively. KGs also facilitate insights, inference, and reasoning. Traditional NLP methods, such as named entity recognition and relation extraction, are key in information retrieval but face limitations, including the use of predefined entity types and the need for supervised learning. Current research leverages large language models' capabilities, such as zero-or few-shot learning. However, unresolved and semantically duplicated entities and relations still pose challenges, leading to inconsistent graphs and requiring extensive post-processing. Additionally, most approaches are topic-dependent. In this paper, we propose iText2KG, a method for incremental, topic-independent KG construction without post-processing. This plug-and-play, zero-shot method is applicable across a wide range of KG construction scenarios and comprises four modules: Document Distiller, Incremental Entity Extractor, Incremental Relation Extractor, and Graph Integrator and Visualization. Our method demonstrates superior performance compared to baseline methods across three scenarios: converting scientific papers to graphs, websites to graphs, and CVs to graphs.
Fichier principal
Vignette du fichier
2409.03284v1.pdf (2.5 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Licence

Dates and versions

hal-04780445 , version 1 (13-11-2024)

Licence

Identifiers

Cite

Yassir Lairgi, Ludovic Moncla, Rémy Cazabet, Khalid Benabdeslem, Pierre Cléau. iText2KG: Incremental Knowledge Graphs Construction Using Large Language Models. 25th International Conference on Web Information Systems Engineering (WISE 2024), Dec 2024, Doha, Qatar. ⟨10.48550/arXiv.2409.03284⟩. ⟨hal-04780445⟩
0 View
0 Download

Altmetric

Share

More