In this talk, I will describe three research problems I have recently worked on and found worth further discussion and investigation in the context of neural machine translation. First, I will discuss whether the standard autoregressive sequence model could be replaced with non-autoregressive one and if so, how we would do so by introducing the idea of iterative refinement for sequence generation. Second, I will introduce one particular type of meta-learning algorithms, called MAML [Finn et al., 2017] and discuss how this is well-suited for multilingual translation and in particular low-resource translation. Lastly, I will quickly discuss slightly old work on real-time translation. All of these works are highly experimental but at the same time extremely fun to think about and discuss.

--

For an interview of Kyunghyun Cho conducted after this talk, please see: https://www.youtube.com/watch?v=s8NJZw2Worc&t=454s .