D4R -- Exploring and Querying Relational Graphs Using Natural Language and Large Language Models -- the Case of Historical Documents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Boeglin, Michel, Kahn, David, Mothe, Josiane, Ortiz, Diego, Panzoli, David
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916663447781376
author Boeglin, Michel
Kahn, David
Mothe, Josiane
Ortiz, Diego
Panzoli, David
author_facet Boeglin, Michel
Kahn, David
Mothe, Josiane
Ortiz, Diego
Panzoli, David
contents D4R is a digital platform designed to assist non-technical users, particularly historians, in exploring textual documents through advanced graphical tools for text analysis and knowledge extraction. By leveraging a large language model, D4R translates natural language questions into Cypher queries, enabling the retrieval of data from a Neo4J database. A user-friendly graphical interface allows for intuitive interaction, enabling users to navigate and analyse complex relational data extracted from unstructured textual documents. Originally designed to bridge the gap between AI technologies and historical research, D4R's capabilities extend to various other domains. A demonstration video and a live software demo are available.
format Preprint
id arxiv_https___arxiv_org_abs_2503_20914
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle D4R -- Exploring and Querying Relational Graphs Using Natural Language and Large Language Models -- the Case of Historical Documents
Boeglin, Michel
Kahn, David
Mothe, Josiane
Ortiz, Diego
Panzoli, David
Information Retrieval
Artificial Intelligence
Computation and Language
Machine Learning
H.3; H.3.3; I.2.7
D4R is a digital platform designed to assist non-technical users, particularly historians, in exploring textual documents through advanced graphical tools for text analysis and knowledge extraction. By leveraging a large language model, D4R translates natural language questions into Cypher queries, enabling the retrieval of data from a Neo4J database. A user-friendly graphical interface allows for intuitive interaction, enabling users to navigate and analyse complex relational data extracted from unstructured textual documents. Originally designed to bridge the gap between AI technologies and historical research, D4R's capabilities extend to various other domains. A demonstration video and a live software demo are available.
title D4R -- Exploring and Querying Relational Graphs Using Natural Language and Large Language Models -- the Case of Historical Documents
topic Information Retrieval
Artificial Intelligence
Computation and Language
Machine Learning
H.3; H.3.3; I.2.7
url https://arxiv.org/abs/2503.20914