Dynamic Named Entity Recognition - Laboratoire Interdisciplinaire des Sciences du Numérique Access content directly
Conference Papers Year : 2023

Dynamic Named Entity Recognition

Tristan Luiggi
Siwar Jendoubi
Aurelien Baelde

Abstract

Named Entity Recognition (NER) is a challenging and widely studied task that involves detecting and typing entities in text. So far, NER still approaches entity typing as a task of classification into universal classes (e.g. date, person, or location). Recent advances in natural language processing focus on architectures of increasing complexity that may lead to overfitting and memorization, and thus, underuse of context. Our work targets situations where the type of entities depends on the context and cannot be solved solely by memorization. We hence introduce a new task: Dynamic Named Entity Recognition (DNER), providing a framework to better evaluate the ability of algorithms to extract entities by exploiting the context. The DNER benchmark is based on two datasets, DNER-RotoWire and DNER-IMDb. We evaluate baseline models and present experiments reflecting issues and research axes related to this novel task.
Fichier principal
Vignette du fichier
sac23.pdf (968.85 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04284318 , version 1 (14-11-2023)

Identifiers

Cite

Tristan Luiggi, Vincent Guigue, Laure Soulier, Siwar Jendoubi, Aurelien Baelde. Dynamic Named Entity Recognition. 38th ACM/SIGAPP Symposium on Applied Computing, Mar 2023, Tallinn, Estonia. pp.890-897, ⟨10.1145/3555776.3577603⟩. ⟨hal-04284318⟩
28 View
16 Download

Altmetric

Share

Gmail Facebook X LinkedIn More