chaitjo / personalized-dialog

Code for the paper 'Personalization in Goal-oriented Dialog' (NeurIPS 2017 Conversational AI Workshop)
https://chaitjo.github.io/personalization-in-dialog/
MIT License
132 stars 45 forks source link

is this possible to modeling multi turn dialog.......here is new dataset #4

Closed SeekPoint closed 7 years ago

SeekPoint commented 7 years ago

https://nlp.stanford.edu/blog/a-new-multi-turn-multi-domain-task-oriented-dialogue-dataset/

chaitjo commented 7 years ago

Hey @loveJasmine , if your intention is to use the Memory Network model for this dataset, I don't see why it should not be possible. although I am not sure this would be the best model for this task in terms of performance. You may have to make the model generate an output instead of discriminate one depending on how they have framed their evaluation.