varsha33/lcl_loss

lcl_loss's Issues

could you provide the yaml file for building the environment for running the code?

Hey,

could you provide the yaml file (or any other format) for building the environment for running the code?

Thanks in advance

Optimize the training speed

I suggest that you use matrix operations rather than for-loop to construct the weighted_mask.

The for-loop is a bottleneck, which slows down the training speed.

The performance of the model is getting worse and worse as I training the model

I train this model in the empathetic dialogue dataset and I find that as the epoch becomes bigger, the performance of the model is getting worse and worse. I have tried to run the model in several rand seeds by it is still the same, I want to know why.

Question about the code for loss

Hi,

I didn't understand much about this line in code. Is this an engineering need?

        logits_max, _ = torch.max(anchor_dot_contrast, dim=1, keepdim=True)
        logits = anchor_dot_contrast - logits_max.detach()

The classes in 4-hard-d

Hey,

In the paper, the 4-hard-d is {Anticipating, Excited, Hopeful, Guilty}. We re-ran all the experiments in section 5.3 "case study" and found the one for 4-hard-d is very different from what is reported in the paper while other results are similar. Just wondering if by any chance you could double-check your experiment to see whether the classes in 4-hard-d are correct? BTW they seem to be less "hard" than 4-hard-a/b/c...

How many epochs we need to reproduce the experimental results?

Hey,

I checked the paper and noticed that the number of epochs needed is not specified in the paper- would much appreciate it if you could provide the number of epochs needed for each data coz I found that setting it to 5 (as in the code) for the ed dataset cannot produce the accuracy as reported.

Thanks!

config.py Parameters

Hi. Thanks for the great repo. I was wondering what other values can each of the below parameters get in the config.py file. Since they are strings and should be accurate, I would appreciate it if you could provide all the possible values. Thank you.

criterion 
loss_type
model_type

The empathetic_dialogue raw data does not have the field "emotion"

Do you mean "context" in the following code?

https://github.com/varsha33/LCL_loss/blob/master/data_preprocess.py#L44

a question for model structure---

i notice that the contextual text encoder also has a classifier branch for classification, why not just using the result of this classifier as weighting? is there some reason to train another weighting network ?

About Eq.3

Hey,

I think if you really meant to place w outside of log in Eq.3, then in this line it should time logits_mask instead of weighted_mask, right?

Thanks