))
Philipp Koehn (Part 1) - How Neural Networks Have Transformed Machine Translation
Manage episode 297999658 series 2954151
Innhold levert av Damien Deighan and Philipp Diesinger, Damien Deighan, and Philipp Diesinger. Alt podcastinnhold, inkludert episoder, grafikk og podcastbeskrivelser, lastes opp og leveres direkte av Damien Deighan and Philipp Diesinger, Damien Deighan, and Philipp Diesinger eller deres podcastplattformpartner. Hvis du tror at noen bruker det opphavsrettsbeskyttede verket ditt uten din tillatelse, kan du følge prosessen skissert her https://no.player.fm/legal.
Professor Philipp Koehn of Johns Hopkins University discusses the evolution of machine translation and the fundamentals for using Neural Networks to deliver Machine translation.
Episode Summary:
- Philipp Koehn Bio
- What is Machine Translation?
- Adequacy & Fluency
- How to Quantify the performance of Machine Translation models
- The Transition from Statistical approaches to using Neural Networks for translation
- Validating Outputs of models
- What can go wrong with Machine Translation?
Resources:
Philipp Koehn latest book - Neural Machine Translation - Amazon link:
https://www.amazon.com/Neural-Machine-Translation-Philipp-Koehn/dp/1108497322
25 episoder
Del
