HMT
HMT copied to clipboard
ictnlp
Source code for ICLR 2023 spotlight paper "Hidden Markov Transformer for Simultaneous Machine Translation"
Hi Shaolei, Thanks for releasing the checkpoints. Do you mind also uploading the corresponding binary data for reproducing? Also, I wonder how you evaluate the AL. Are you using the...
I used **L=3, K=6 WMT2015 de-en Transformer-Base** to reproduce the results of the paper, but the bleu value was nearly 1.64 lower than the original paper.  **As shown in...
The link to L=11 model weights is broken. Could you please update it?
