U.S. Department of Energy

Pacific Northwest National Laboratory

A New Territory of Machine Translation

Wednesday, March 2, 2016
Dr. Kyunghyun Cho
Assistant Professor of Computer Science and Data Science
New York University
Neural machine translation has just been introduced to the field of natural language processing and machine translation. Unlike existing approaches to machine translation, neural machine translation tackles the problem of translation by directly modelling the conditional probability of a translation given a source sentence without any assumption on factorization. Already in less than a year, neural machine translation has proven itself to be competitive against the existing translation approaches in many language pairs, which has excited many researchers in the field. In this talk, instead of telling you how neural machine translation has been successful at the existing setting of machine translation, I describe new opportunities in machine translation that have become possible by introducing deep learning to machine translation. These opportunities include sub-word/character-level translation, multilingual translation, and larger-context modelling.
Speaker Bio

Kyunghyun Cho is an assistant professor of Computer Science and Data Science at New York University (NYU). Before he started at NYU on September 2015, he was a postdoctoral researcher at the University of Montreal under the supervision of Prof. Yoshua Bengio. He received his doctorate degree at Aalto University (Finland) in early 2014. Kyunghyun's main research interests include neural networks, and generative models and their applications, especially to language understanding.

| Pacific Northwest National Laboratory