A SkillsCast for this session is not available.
Statistical Machine Translation is the task of translating natural languages using statistical models. Aurelien is introducing Scala and Spark into his translation pipeline and finding it a good fit for many of the problems faced. You will learn about the Scala based rule extractor, how Spark makes extracting data about N-grams trivial, and Aurelien's experience using Spark with deep learning frameworks.
YOU MAY ALSO LIKE:
- Lightning Talks 2 (SkillsCast recorded in December 2015)
- Deep Learning Fundamentals with Leonardo De Marchi (Online Course on 8th - 11th February 2021)
- Abstract Data Types In The Region Of Abysmal Pain, And How To Navigate Them (SkillsCast recorded in September 2019)
- Deep Learning for Magnetic Resonance Imaging (SkillsCast recorded in September 2019)
Scala and Statistical Machine Translation
Aurelien is a research scientist at SDL Research, specialising in Machine Translation. He completed his Ph.D at the University of Cambridge under the supervision of Prof. Bill Byrne