metadata

license: cc0-1.0
language:
  - en
tags:
  - archaeology
  - english

ArchaeoBERT

An English BERT model for the Archaeology domain

This model is based on the bert-base-cased model (https://huggingface.co/bert-base-cased).

We further finetuned bert-base-cased with a corpus of roughly 44k documents (~264 million tokens) from the ADS library (https://archaeologydataservice.ac.uk/library/index.xhtml).