Author of post here. I'd say most of the examples generated from the best model were good. However we chose examples that were not too gruesome, as news can be :)
We encourage you to try the code and see for yourself.
We encourage you to try the code and see for yourself.
[1] That is, the problem of selecting a sentence such as "He approved the motion" and then realising that "he" is now undefined.
As for how does the model deal with co-reference? There's no special logic for that.
>>"In those tasks training from scratch with this model architecture does not do as well as some other techniques we're researching, but it serves as a baseline."
Can you elaborate a little on that? Is the training the problem or is the model just not good at longer texts?
I've seen copynet, where you do seq2seq but also have a copy mechanism to copy rare words from the source sentence to the target sentence.