Fine-tuned Flair Model on CO-Fun NER Dataset

This Flair model was fine-tuned on the CO-Fun NER Dataset using German BERT as backbone LM.

Dataset

The Company Outsourcing in Fund Prospectuses (CO-Fun) dataset consists of 948 sentences with 5,969 named entity annotations, including 2,340 Outsourced Services, 2,024 Companies, 1,594 Locations and 11 Software annotations.

Overall, the following named entities are annotated:

The latest Flair version is used for fine-tuning.

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

More details can be found in this repository. All models are fine-tuned on a Hetzner GEX44 with an NVIDIA RTX 4000.

A hyper-parameter search with 5 different seeds per configuration is performed and micro F1-score on development set is reported:

Configuration	Seed 1	Seed 2	Seed 3	Seed 4	Seed 5	Average
`bs8-e10-lr5e-05`	0.9346	0.9388	0.9301	0.9291	0.9346	0.9334 ± 0.0039
`bs16-e10-lr5e-05`	0.9316	0.9328	0.9341	0.9315	0.9248	0.931 ± 0.0036
`bs8-e10-lr3e-05`	0.9234	0.9391	0.9207	0.9191	0.9394	0.9283 ± 0.0101
`bs16-e10-lr3e-05`	0.9136	0.9269	0.9231	0.9251	0.9247	0.9227 ± 0.0053

The result in bold shows the performance of the current viewed model.

Additionally, the Flair training log and TensorBoard logs are also uploaded to the model hub.