Arretium or Arezzo? A Neural Approach to the Identification of Place Names in Historical Texts

Risultato della ricerca: Contributo in libroContributo a convegno

Abstract

This paper presents the application of a neural architecture to the identification of place names in English historical texts. We test the impact of different word embeddings and we compare the results to the ones obtained with the Stanford NER module of CoreNLP before and after the retraining using a novel corpus of manually annotated historical travel writings.
Lingua originaleEnglish
Titolo della pubblicazione ospiteProceedings of the Fifth Italian Conference on Computational Linguistics (CLiC-it 2018)
Pagine360-365
Numero di pagine6
Stato di pubblicazionePubblicato - 2018
EventoFifth Italian Conference on Computational Linguistics (CLiC-it 2018) - Torino, Italy
Durata: 10 dic 201812 dic 2018

Convegno

ConvegnoFifth Italian Conference on Computational Linguistics (CLiC-it 2018)
CittàTorino, Italy
Periodo10/12/1812/12/18

Keywords

  • named entity recognition, annotation, information extraction, historical texts, travel writings

Cita questo