Fine-tuned Flair Model on French HIPE-2020 Dataset (HIPE-2022)

This Flair model was fine-tuned on the French HIPE-2020 NER Dataset using hmBERT 64k as backbone LM.

The HIPE-2020 dataset is comprised of newspapers from mid 19C to mid 20C. For information can be found here.

The following NEs were annotated: loc, org, pers, prod, time and comp.

Results

We performed a hyper-parameter search over the following parameters with 5 different seeds per configuration:

And report micro F1-score on development set:

Configuration	Seed 1	Seed 2	Seed 3	Seed 4	Seed 5	Average
`bs8-e10-lr3e-05`	0.8389	0.8466	0.8299	0.8391	0.8427	0.8394 ± 0.0062
`bs4-e10-lr3e-05`	0.8279	0.8364	0.8404	0.8382	0.8371	0.836 ± 0.0048
`bs8-e10-lr5e-05`	0.8418	0.8337	0.831	0.8346	0.8352	0.8353 ± 0.004
`bs4-e10-lr5e-05`	0.831	0.8239	0.7784	0.8313	0.8191	0.8167 ± 0.022

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.

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 ❤️