Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Yes but.. Can ChatGPT Identify Entities in Historical Documents?
 
conference paper

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 Can ChatGPT Identify Entities in Historical Documents?

Gonzalez-Gallardo, Carlos-Emiliano
•
Boros, Emanuela  orcid-logo
•
Girdhar, Nancy
Show more
January 1, 2023
2023 Acm/Ieee Joint Conference On Digital Libraries, Jcdl
23rd ACM/IEEE Joint Conference on Digital Libraries (JCDL)

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.

  • Details
  • Metrics
Type
conference paper
DOI
10.1109/JCDL57899.2023.00034
Web of Science ID

WOS:001098971300024

Author(s)
Gonzalez-Gallardo, Carlos-Emiliano
•
Boros, Emanuela  orcid-logo
•
Girdhar, Nancy
•
Hamdi, Ahmed
•
Moreno, Jose G.
•
Doucet, Antoine
Corporate authors
ACM
Date Issued

2023-01-01

Publisher

Assoc Computing Machinery

Publisher place

New York

Published in
2023 Acm/Ieee Joint Conference On Digital Libraries, Jcdl
ISBN of the book

979-8-3503-9931-8

Start page

184

End page

189

Subjects

Technology

•

Named Entity Recognition And Classification

•

Large Language Models

•

Generative Pretrained Transformer

•

Historical Documents

Editorial or Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
DHLAB  
Event nameEvent placeEvent date
23rd ACM/IEEE Joint Conference on Digital Libraries (JCDL)

Santa Fe, NM

JUN 26-30, 2023

FunderGrant Number

ANNA

2019-1R40226

TER-MITRAD

AAPR2020-2019-8510010

Pypa

AAPR2021-2021-12263410

Show more
Available on Infoscience
February 20, 2024
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/204349
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés