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 Can ChatGPT Identify Entities in Historical Documents?

by   Carlos-Emiliano González-Gallardo, et al.
University of La Rochelle

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.


page 1

page 2

page 3

page 4


Entities, Dates, and Languages: Zero-Shot on Historical Texts with T0

In this work, we explore whether the recently demonstrated zero-shot abi...

VicunaNER: Zero/Few-shot Named Entity Recognition using Vicuna

Large Language Models (LLMs, e.g., ChatGPT) have shown impressive zero- ...

Named Entity Recognition and Classification on Historical Documents: A Survey

After decades of massive digitisation, an unprecedented amount of histor...

Transformer-Based Approach for Joint Handwriting and Named Entity Recognition in Historical documents

The extraction of relevant information carried out by named entities in ...

Temporal Concept Drift and Alignment: An empirical approach to comparing Knowledge Organization Systems over time

This research explores temporal concept drift and temporal alignment in ...

HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient Korea

Historical records in Korea before the 20th century were primarily writt...

Unsilencing Colonial Archives via Automated Entity Recognition

Colonial archives are at the center of increased interest from a variety...

Please sign up or login with your details

Forgot password? Click here to reset