Paweł Budzianowski

If you change topk to a larger number, the algorithm will generate more hypotheses as the `number_required` variable is dependent on it.

The algorithm generates the sentence using the beam search based on the priority queue (line 96). The while loop works until top-k sentences are generated (the generation of the sentence...

Hi, can you explain in more detailed what models you evaluated?

Hi, thanks for catching this! It's a bug! However, due to backwards compatibility with previous results, it won't be easy to fix that straight away. I will try to come...

Hi! thanks for raising this. Indeed the scores will be slightly different (up to 0.5% in my experience). The randomness models the real life problem where often the system can...

I'm not sure what you exactly need. Can you give an example?

I can report the same issue, any news on this @Savevska ?