Re:Teaching an AI to write Python code with Python code
by transcranial on Thursday July 14, 2016 @12:45PM
(#12095348)
The problem is that the latent space of a model trained on all comments is still massive. For any sort of coherence, you need to condition the probabilities on smaller spaces, or enforce structural bounds.
Here's an example of a paper where they simultaneously optimize high-level semantics with token-level sequence probabilities: http://arxiv.org/pdf/1606.00776v2.pdf.
Does anyone has any suggestions on papers that try to solve that problem?