search

dongjun-Lee / text-summarization-tensorflow

Tensorflow seq2seq Implementation of Text Summarization.
MIT License
637 stars 196 forks source link

Number of output (in result.txt) is much smaller than number of input data. #38

Open guchanist opened 5 years ago

guchanist commented 5 years ago

I am a newbie in deep learning. While self-studying seq2seq model, I try to modify this code so that it can be applicable to another language. However, I faced one critical issue that the number of my output data (in result.txt) generated is much shorter than the number of input data.

Here are some differences in my code.

  1. tensorflow version 1.10.
  2. pretrained fasttext embedding instead of glove.

I first want to make the overall process work then optimize or train the model with more data. But, I got stuck in this issue for a couple days. Wonder if you have any idea what can possibly cause above issue.