Historical Multilingual Language Models for Named Entity Recognition. The following languages are covered by hmBERT:
More details can be found in our GitHub repository and in our hmBERT paper.
The hmBERT 64k model is a 12-layer BERT model with a 64k vocab.
We test our pretrained language models on various datasets from HIPE-2020, HIPE-2022 and Europeana. The following table shows an overview of used datasets:
| Language | Datasets |
|---|---|
| English | AjMC - TopRes19th |
| German | AjMC - NewsEye - HIPE-2020 |
| French | AjMC - ICDAR-Europeana - LeTemps - NewsEye - HIPE-2020 |
| Finnish | NewsEye |
| Swedish | NewsEye |
| Dutch | ICDAR-Europeana |
All results can be found in the hmLeaderboard.
We thank Luisa März, Katharina Schmid and Erion Çano for their fruitful discussions about Historical Language Models.
Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC). Many Thanks for providing access to the TPUs ❤️