Entities, Dates, and Languages: Zero-Shot on Historical Texts with T0 - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2022

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

Abstract

In this work, we explore whether the recently demonstrated zero-shot abilities of the T0 model extend to Named Entity Recognition for out-of-distribution languages and time periods. Using a historical newspaper corpus in 3 languages as test-bed, we use prompts to extract possible named entities. Our results show that a naive approach for prompt-based zero-shot multilingual Named Entity Recognition is error-prone, but highlights the potential of such an approach for historical languages lacking labeled datasets. Moreover, we also find that T0-like models can be probed to predict the publication date and language of a document, which could be very relevant for the study of historical texts.

Dates and versions

hal-03639144 , version 1 (12-04-2022)

Identifiers

Cite

Francesco de Toni, Christopher Akiki, Javier de La Rosa, Clémentine Fourrier, Enrique Manjavacas, et al.. Entities, Dates, and Languages: Zero-Shot on Historical Texts with T0. BigScience 2022 - International Workshop on Challenges & Perspectives in Creating Large Language Models 2022, May 2022, Dublin, Ireland. ⟨hal-03639144⟩

Collections

INRIA INRIA2
54 View
0 Download

Altmetric

Share

More