Fine-Grained Named Entity Recognition, a stack of models to infer benefit details from lengthy Insurance Contracts and Booklets. The models are based on the French language, achieving a Coarse-Grained Entity Accuracy of 100%, and the following scores for Fine-Grained Entity Recognition:
F-score for FG models for each CG type:
-
Amounts: 94%
-
Percentages: 83%
-
Ages: 81%
-
Duration: 82%