A Two-Step Approach for Explainable Relation Extraction - Archive ouverte HAL Access content directly
Conference Papers Year :

A Two-Step Approach for Explainable Relation Extraction

Hugo Ayats
Peggy Cellier
Sébastien Ferré

Abstract

Knowledge Graphs (KG) offer easy-to-process information. An important issue to build a KG from texts is the Relation Extraction (RE) task that identifies and labels relationships between entity mentions. In this paper, to address the RE problem, we propose to combine a deep learning approach for relation detection, and a symbolic method for relation classification. It allows to have at the same time the performance of deep learning methods and the interpretability of symbolic methods. This method has been evaluated and compared with state-ofthe-art methods on TACRED, a relation extraction benchmark, and has shown interesting quantitative and qualitative results.
Fichier principal
Vignette du fichier
IDA_2022_final.pdf (596.62 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03866083 , version 1 (22-11-2022)

Identifiers

  • HAL Id : hal-03866083 , version 1

Cite

Hugo Ayats, Peggy Cellier, Sébastien Ferré. A Two-Step Approach for Explainable Relation Extraction. IDA 2022 - Symposium on Intelligent Data Analysis, Apr 2022, Rennes, France. pp.1-12. ⟨hal-03866083⟩
34 View
20 Download

Share

Gmail Facebook Twitter LinkedIn More