Chatbot tutorial question

I’m following the chatbot tutorial at this URL.

I’ve written two Modules. One is a decoder and one is an encoder. They run. My problem is that when I look at my output, quite often I just see the word ‘I’ alone. In other words the chatbot thinks that it is sufficient to answer every question with the word ‘I’ alone. I donwloaded the code from the tutorial and that code does not show this behaviour.

I’ve tried a tensorflow project, and though it was a long time ago I believe I remember having this same problem. I am using the movie database as my corpus. I have to think someone has seen this problem before.

My setup currently is that the encoder processes a whole batch at a time, while the decoder goes through the batch line by line and the lines word by word. Is this my problem?

my code changes often and is very messy, but the url to the seq2seq model on github is here:

any help would be appreciated.

Your code is quite long (~2800 lines of code), so that it would be helpful if you could narrow down possible issues to some functions.
I’m not an NLP expert, but usually it helps me to scale down the problem, i.e. use a simple model, little dataset, and check my code for possible bugs.

why don’t you write a meaningful title for your question? What issue/question? Can I know your question/issue just by reading your question title?