DialogWAE

DialogWAE copied to clipboard

Code explanation about data prepocessing

2

Hello, thank for your open source. I am trying to understand your code. However, in the data.py, it is confused for me to preprocess the data. In building vocabulary, ```python...

sinlin0908

Unable to achieve published result in DailyDialogue

3

Hi, I am trying to retrain your model as a baseline, and till now SWDA gave the results as per the paper. actually, slightly better. But for the DailyDialog dataset,...

bsantraigi

It is reasonable if I set n_samples to 1 when I run the sample.py

2

li3cmz

seems the loss of both generator and discriminator would collapse?

1

Hello, I am running your code with SWDA dataset but the loss going like this: train_loss_AE:2.7721 train_loss_G:298.7391 train_loss_D:-300.4698 DialogWAE_GMP-basic|SWDA@gpu0 epo:[84/100] iter:[1200/1279] step_time:56s elapsed:0:11:33

sszzsupersupersupersuper

Wasserstein distance between prior and posterior

3

Hi, I'm trying to find the part of the code that attempts to compute the Wasserstein distance between prior and posterior (as in Eq. 5 in your ICLR paper), but...

sadegh-aa

SWDA seems to give lot of repetition in the sample responses for the test data.

4

**Context 4-1:** ('yeah ', 2) **Context 5-0:** ("and the people in the city were saying well why should i go do that make the government do that that ' s...

vishakha-bansal