Published June 30, 2023 | Version v1

Large Language Models and NER: better results with less work

  • 1. Cornell University, United States of America
  • 1. University of Graz
  • 2. Belgrade Center for Digital Humanities
  • 3. Le Mans Université
  • 4. Digital Humanities im deutschsprachigen Raum

Description

Our work considers how new advances in pretrained text-to-text generation models might make named entity recognition more accurate, flexible, and streamlined for the digital humanist. We provide an example of how text-to-text generative models can identify mentions of characters, authors, and book names within Goodreads book reviews.

Files

Thalken_Large-Language-Models-and-NER.pdf

Files (1.7 MB)

Name Size Download all
md5:727ce7ea8e4ba7ba42916b28f7e85cba
1.7 MB Preview Download

Additional details

Related works

Is supplement to
Conference paper: 10.5281/zenodo.8107551 (DOI)