TransformerQA
Implemented By:
-
Dirk Groeneveld
-
Akshita Bhagia
-
Pete Walsh
Description:
This model solves the reading comprehension model task. It is similar to the proposed model in Devlin et al, with improvements borrowed from the SQuAD model in the transformers project.
This model is maintained by the AllenNLP team and its contributors on the AllenNLP models repository at https://github.com/allenai/allennlp-models.
It achieves 88% F1 and 84% exact match on the SQuAD 2.0 validation set.