Multilevel Entity-Informed Business Relation Extraction - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Multilevel Entity-Informed Business Relation Extraction

(1, 2) , (2) , (1) , (2) , (1)
1
2

Abstract

This paper describes a business relation extraction system that combines contextualized language models with multiple levels of entity knowledge. Our contributions are three-folds: (1) a novel characterization of business relations, (2) the first large English dataset of more than 10k relation instances manually annotated according to this characterization, and (3) multiple neural architectures based on BERT, newly augmented with three complementary levels of knowledge about entities: generalization over entity type, pre-trained entity embeddings learned from two external knowledge graphs, and an entity-knowledge-aware attention mechanism. Our results show an improvement over many strong knowledge-agnostic and knowledge-enhanced state of the art models for relation extraction.
Fichier principal
Vignette du fichier
NLDB_ICWE_conf21_.pdf (299.79 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03329307 , version 1 (30-08-2021)

Identifiers

Cite

Hadjer Khaldi, Farah Benamara, Amine Abdaoui, Nathalie Aussenac-Gilles, Eunbee Kang. Multilevel Entity-Informed Business Relation Extraction. 26th International Conference on Applications of Natural Language to Information Systems (NLDB 2021), Jun 2021, Saarbrücken (on line), Germany. pp.105-118, ⟨10.1007/978-3-030-80599-9_10⟩. ⟨hal-03329307⟩
90 View
115 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More