-
**Describe the feature**
Add data processing code for the following models using the standard transformations #14 and evaluate using #15.
NLU:
- [x] MILU
- [x] BERTNLU
DST:
- [ ] TRADE
- [x…
-
When I run python main.py --pretrain True --save_dir model_wgan/emnlp_model_agenda_pre_nosimgan_epoch9_temp0.01_action0.1_clip0.01_2 --epoch 16 --gan_type wgan --temperature 0.001 --action_lambda 0. -…
-
Why the benchmark table shows very bad result of the methods that reach state-of-the-arts performance in Multiwoz benchmark table? And also like, GDPL, why it performs very bad under this framework?
-
**Describe the bug**
After the recent mailblast actually revealed the mail address of at least 500 contributors against each others (by using the To: field)...
) mentioned in your paper?
And also, the ["AIRL"]…
-
**Describe the bug**
When I try to train the model of GDPL, also I loaded the MLE pretrained model, but the loss and results for evluation is always around 0.26. Below is the problem issue, could you…
-
When training policies that use the `UserPolicyAgendaMultiWoz` such as `PG`, `PPO` and `GDPL`, it throws an Exception.
This Exception is related to the file `convlab2/task/multiwoz/goal_generator.py`…
-
Dear,
Thank you for proposing an impressive work. Could you release the code about ACER and pure PPO in “Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog”?