MeanSum

MeanSum copied to clipboard

Cant Find the reconstruction part

2

Hi@sosuperic , According to the paper, when we back propagates the model, there should be an autoencoder reconstruction loss and average summary similarity loss, but I couldn't find the code...

V-Enzo

There is a bug in the implementation of the extractive baseline you are using, mentioned here: https://github.com/gaetangate/text-summarizer/pull/5 Did you fix that bug before evaluating this model?

blazejdolicki

hi , when i train the No pre-trained language model ,why the nll loss is Nan sometimes ?

1204271075

About the Discriminator model

1

hello , i have a question. I can't find the model path in project_settings.py and the class Discriminator that appears in train_sum.py also not found

1204271075

About the file ''subwordenc_32000_maxrevs260_fixed.pkl''

1

hello , i want to reduce the size of the vocabulary ， can you provied the python file that produced the "subwordenc_32000_maxrevs260_fixed.pkl'"

1204271075

When i change the batch_size = 16 , emb_size = 32 , and hidden_size = 64 , the text_cnn.py throughs a error : RuntimeError: Expected 4-dimensional input for 4-dimensional weight...

1204271075