A Bert2Bert model on the Wiki Summary dataset to summarize articles. The model achieved an 8.47 ROUGE-2 score.

For more detail, please follow the Wiki Summary repo.

Eval results

The following table summarizes the ROUGE scores obtained by the Bert2Bert model.

% Precision Recall FMeasure
ROUGE-1 28.14 30.86 27.34
ROUGE-2 07.12 08.47* 07.10
ROUGE-L 28.49 25.87 25.50

Questions?

Post a Github issue on the Wiki Summary repo.

Downloads last month
4
Hosted inference API
Summarization