ledw-2

@lshowway Hi, sorry for the delay in responding. The bi-encoder and cross encoder are optimized separately. For those equations, they are all independent. To be more specific: 1. Use eq.4...

Hi @clintoncheang, we did not compute f1 so you would need to implement that yourself. For other metrics, look at code here https://github.com/facebookresearch/BLINK/blob/main/blink/main_dense.py#L476 (and in similar places for cross-encoder).

@abhinavkulkarni Thanks for the comments! I hope you find this project useful to you.😃

Sorry for not updating on this. The token_idx are generated from BERT tokenizers. The format is batch x vec where vec is the BERT token id vector of input. It's...