Tiancheng Zhao (Tony)

Same request here :)

I am very interested in this too and would love to work together. I have research experience in both DeepCT and vector-based search.

Thata's on my dev list now. I am going to shoot for Deep CT sparse vector instead of dense vector, since that can be done by reusing the current inverted...

Please take look at this solution to issue #815 #936

That should cause a problem in a single run right?

The code is written in Python 2.7. Thanks!

Please report your running environment

Thanks for pointing that out. I will change the order.

You can probably modify the decoding function inside: NeuralDialog-CVAE/models/decoder_fn_lib.py

Same problem here. The client can emit but never get message from other clients.