Vicomtech at CAPITEL 2020: Facing Entity Recognition and Universal Dependency Parsing of Spanish News Articles with BERT Models

Abstract

These working notes describe the participation of Vicomtech NLP team in the CAPITEL task, whichis part of the IberLEF 2020. CAPITEL task included two sub-tasks: Named Entity Recognition andClassification (NERC) and Universal Dependency (UD) Parsing for Spanish news articles. A specificsystem has been designed for each task based on BERT architectures. Both systems have been testedwith different settings, where the best ones have been selected for being submitted to the shared task.The resulting systems show robust and competitive systems in both tasks with simple architectures.

BIB_text

@Article {
title = {Vicomtech at CAPITEL 2020: Facing Entity Recognition and Universal Dependency Parsing of Spanish News Articles with BERT Models},
pages = {52-59},
keywds = {
NER, Dependency Parsing
}
abstract = {

These working notes describe the participation of Vicomtech NLP team in the CAPITEL task, whichis part of the IberLEF 2020. CAPITEL task included two sub-tasks: Named Entity Recognition andClassification (NERC) and Universal Dependency (UD) Parsing for Spanish news articles. A specificsystem has been designed for each task based on BERT architectures. Both systems have been testedwith different settings, where the best ones have been selected for being submitted to the shared task.The resulting systems show robust and competitive systems in both tasks with simple architectures.


}
date = {2020-09-22},
}
Vicomtech

Parque Científico y Tecnológico de Gipuzkoa,
Paseo Mikeletegi 57,
20009 Donostia / San Sebastián (Spain)

+(34) 943 309 230

close overlay