Yes but.. Can ChatGPT Identify Entities in Historical Documents? - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Yes but.. Can ChatGPT Identify Entities in Historical Documents?

Résumé

Large language models (LLMs) have been leveraged for several years now, obtaining state-of-the-art performance in recognizing entities from modern documents. For the last few months, the conversational agent ChatGPT has "prompted" a lot of interest in the scientific community and public due to its capacity of generating plausible-sounding answers. In this paper, we explore this ability by probing it in the named entity recognition and classification (NERC) task in primary sources (e.g., historical newspapers and classical commentaries) in a zero-shot manner and by comparing it with state-of-the-art LM-based systems. Our findings indicate several shortcomings in identifying entities in historical text that range from the consistency of entity annotation guidelines, entity complexity, and code-switching, to the specificity of prompting. Moreover, as expected, the inaccessibility of historical archives to the public (and thus on the Internet) also impacts its performance.

Fichier principal
Vignette du fichier
2303.17322v1.pdf (613.37 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04676769 , version 1 (23-08-2024)

Identifiants

Citer

Carlos-Emiliano González-Gallardo, Emanuela Boros, Nancy Girdhar, Ahmed Hamdi, Jose G. Moreno, et al.. Yes but.. Can ChatGPT Identify Entities in Historical Documents?. 2023 ACM/IEEE Joint Conference on Digital Libraries (JCDL), Jun 2023, Santa Fe, United States. pp.184-189, ⟨10.1109/JCDL57899.2023.00034⟩. ⟨hal-04676769⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More