Anyone can create a custom MT engine by simply uploading data and training. However, much like in a kitchen, just throwing ingredients in a pot does not make a great meal. A good recipe, a skilled chief, and the right tools will give a much better result. Similarly, a great translation engine that consistently delivers substantially higher quality translations that generic machine translation engines such as Google, requires expertise and experience.

Did you know that the latest MT engines are built on more than 1 billion bilingual sentences? We will go step-by-step through the process of how the latest document context technologies are used in the MT engine creation process. We will show how much effort that you need to put in and how data is created on such a large scale.

Join Omniscien's Chief Scientist, Professor Philipp Koehn, a leading researcher in the field of AI and MT, along with Dion Wiggins, Omniscien’s CTO, for an hour of information sharing and insights.

This is Part 2 of a 2 part series. Part 1 is titled "Advances in Artificial Intelligence and Machine Translation: 2022 and Beyond" and was presented on Wednesday 17 November 2021.
Watch part 1 here: [ Ссылка ]

свернуть