In Tech-Assisted Interpreting, the Tricky Problem of Non-English ‘Person Names’
New research shows that automatic speech recognition and speech translation systems also improve when training data includes multiple instances of a given name.
SlatorCon Zurich is now SOLD OUT — See you on October 4th!
New research shows that automatic speech recognition and speech translation systems also improve when training data includes multiple instances of a given name.
EU releases complete list of players in contract to automatically transcribe and translate multilingual parliamentary debates in real time; two consortia and Microsoft Belgium awarded for phase one.
Slator’s inaugural comprehensive language industry market report. It examines total market size, the 10 main end-buyer industries, competitive landscape, productivity tech, NMT and much more.
In 2015, four leading European institutions and companies set out to solve machine translation’s four main problems: training, context, scalability, and data collection. After a brief scare when Google Translate went neural, the project is now in beta and set for enterprise-grade release in Q4 2017.
Slator Weekly: Join over 15,800 subscribers and get the latest language industry intelligence every Friday
Tool Box: Join 10,000 subscribers for your monthly linguist technology update.
Your information will not be shared with third parties. No Spam.
This will close in 0 seconds