Exploiting Similarities among Languages for Machine Translation
This presentation will discuss a method that can automate the process of generating and extending dictionaries and phrase tables, which are the basis of modern statistical machine translation systems. This method can translate missing word and phrase entries by learning language structures based on large monolingual data and mapping between languages from small bilingual data. Despite its simplicity, the method is surprisingly effective.
Rob Keizer is an active player in Winnipeg’s tech scene, lending his talents to a variety of entrepreneurial and startup ventures. Rob is currently the Founder and CTO at Pricerazzi, Founder & CEO of Pegboard Hosting, and Director of Coldhak. His previous community involvement has included serving on boards of SkullSpace and the Manitoba Unix User Group (MUUG).