hmbert-tiny/flair-hipe-2022-ajmc-fr

Fine-tuned Flair Model on AjMC French NER Dataset (HIPE-2022)

This Flair model was fine-tuned on the AjMC French NER Dataset using hmBERT Tiny as backbone LM.

The AjMC dataset consists of NE-annotated historical commentaries in the field of Classics, and was created in the context of the Ajax MultiCommentary project.

The following NEs were annotated: pers, work, loc, object, date and scope.

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	0.5346	0.5752	0.543	0.5043	0.5531	0.542 ± 0.026
bs8-e10-lr5e-05	0.4919	0.5134	0.473	0.4909	0.5082	0.4955 ± 0.016
bs4-e10-lr3e-05	0.4902	0.4944	0.4676	0.494	0.4986	0.489 ± 0.0123
bs8-e10-lr3e-05	0.4695	0.4836	0.4372	0.4922	0.5015	0.4768 ± 0.0251

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 ❤️