Continuous representation of language and its implications -- In the case of neural machine translation


Kyunghyung Cho


In this talk, I will go over some of my research on neural machine translation that has happened during the past 2.5 years. Starting from now-standard attention-based neural machine translation, i will walk you through first multilingual translation, search engine guided non-parametric neural machine translation and unsupervised machine translation. Then, I will delve deeper into some of my recent work on decoding algorithms for neural machine translation. If time permits, I will briefly touch upon some of the on-going work at my lab, including non-autoregressive neural machine translation and trainable greedy decoding.


Made on
Tilda