The Role of Global and Local Context in Named Entity Recognition - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

The Role of Global and Local Context in Named Entity Recognition

Abstract

Pre-trained transformer-based models have recently shown great performance when applied to Named Entity Recognition (NER). As the complexity of their self-attention mechanism prevents them from processing long documents at once, these models are usually applied in a sequential fashion. Such an approach unfortunately only incorporates local context and prevents leveraging global document context in long documents such as novels, which might hinder performance. In this article, we explore the impact of global document context, and its relationships with local context. We find that correctly retrieving global document context has a greater impact on performance than only leveraging local context, prompting for further research on how to better retrieve that context.
Fichier principal
Vignette du fichier
2305.03132.pdf (445.29 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Licence : CC BY NC SA - Attribution - NonCommercial - ShareAlike

Dates and versions

hal-04092431 , version 1 (09-05-2023)

Licence

Attribution - NonCommercial - ShareAlike - CC BY 4.0

Identifiers

Cite

Arthur Amalvy, Vincent Labatut, Richard Dufour. The Role of Global and Local Context in Named Entity Recognition. 61st Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Jul 2023, Toronto, Canada. ⟨hal-04092431⟩

Collections

UNIV-AVIGNON LIA
0 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More