morecry / misc Goto Github PK

Hello, the zip file in google drive is broken. Could you re-up your code please? Thanks

Very good work !
About how long it takes to see your code?

Hello,

I was replicating your experiments, and there were some bugs in the code.

1. When running "BlenderEmotionalSupport.py", the sample number of "chat_texts" is inconsistent with that of "comet_st" in line 1183;
2. I tried to reconstruct the "comet_st", but a missing file, named "Situation2Comet.txt", made me stoped;
3. Unfortunately, no other public files can output the "Situation2Comet.txt";

Could you please share more codes or help me figure it out?
Thanks a lot!

After many tries. I have implemented the code.

I have two questions.

1. How did you select the lowest ppl checkpoint? In my case, I trained the model twice, first to see the checkpoints and evals results, then I manually break the training on the checkpoint with the lowest ppl, then train and evaluate the model. Below is the eval result. (the lowest ppl is 16.21 around)
2. Why my eval result is high? Is there something I might be missing? Despite the hyperparameters are the same as in paper.

This is the evaluation result, after training in the same parameter in the paper exp. setup:

{"length": 19.346938775510203, "dist-1": 3.9611914472871095, "dist-2": 17.547699947726084, "dist-3": 32.19769174782518, "bleu-1": 19.537415536727647, "bleu-2": 8.045721170784967, "bleu-3": 4.084835823220594, "bleu-4": 2.3918514292851243, "f1": 20.91022932286169, "rouge-l": 17.504459395975523}

Hi,

When I run your code to train model, it reports an error at the line assert len(df) == len(comet) == len(comet_st), and I find that their lengths are not the same (e.g. for test dataset, one is 1764, the other is 1365). So, how can I solve this problem. Thanks a lot!

求一个运行代码的详细配置环境和所需要的包，谢谢啦