language: en
license: mit
tags:
- flair
- token-classification
- sequence-tagger-model
base_model: dbmdz/bert-tiny-historic-multilingual-cased
widget:
- text: >-
On Wednesday , a public dinner was given by the Conservative Burgesses of
Leads , to the Conservative members of the Leeds Town Council , in the
Music Hall , Albion-street , which was very numerously attended .
Fine-tuned Flair Model on TopRes19th English NER Dataset (HIPE-2022)
This Flair model was fine-tuned on the TopRes19th English NER Dataset using hmBERT Tiny as backbone LM.
The TopRes19th dataset consists of NE-annotated historical English newspaper articles from 19C.
The following NEs were annotated: BUILDING, LOC and STREET.
Results
We performed a hyper-parameter search over the following parameters with 5 different seeds per configuration:
- Batch Sizes:
[4, 8] - Learning Rates:
[5e-05, 3e-05]
And report micro F1-score on development set:
| Configuration | Seed 1 | Seed 2 | Seed 3 | Seed 4 | Seed 5 | Average |
|---|---|---|---|---|---|---|
bs4-e10-lr5e-05 |
0.6681 | 0.5754 | 0.628 | 0.6565 | 0.658 | 0.6372 ± 0.0376 |
bs8-e10-lr5e-05 |
0.6491 | 0.5812 | 0.565 | 0.587 | 0.5938 | 0.5952 ± 0.0319 |
bs4-e10-lr3e-05 |
0.6154 | 0.5782 | 0.5519 | 0.5929 | 0.5931 | 0.5863 ± 0.0234 |
bs8-e10-lr3e-05 |
0.5978 | 0.5489 | 0.528 | 0.5483 | 0.5754 | 0.5597 ± 0.0272 |
The training log and TensorBoard logs (not available for hmBERT Base model) are also uploaded to the model hub.
More information about fine-tuning can be found here.
Acknowledgements
We thank Luisa März, Katharina Schmid and Erion Çano for their fruitful discussions about Historic Language Models.
Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC). Many Thanks for providing access to the TPUs ❤️