- Slides
- Our lecture & seminar (russian)
- English lectures
- Lecture by Mohammad Norouzi - cs294 video
- Alternative lecture by Graham Neubig - CMU nn4nlp video
- Optional lecture on conversation systems - video
- Will hopefully record our lecture in english soon!
- Self-critical sequence traning original article
As usual, go to practice_{your framework}.ipynb above and follow instructions from there. pytorch, tensorflow, theano
- An awesome post explaining attention and long-term memory models.
- BLEU and CIDEr articles.
- Image captioning
- Other articles on reinforcement learning for natural language:
- task-oriented conversation system
- generating dialogues
- sequential adversarial networks (a.k.a. SeqGAN)
- A large overview for machine translation (touching on RL, including RL failures) - arxiv
- How not to evaluate conversation models - arxiv
- Overview of other non-games applications ("that article again") - arxiv