Building Language Technology across the World's Languages
THIS EVENT IS ARCHIVED
Date: 12 December 2018Time: 3:30 PM
Finishes: 12 December 2018Time: 5:00 PM
Venue: Faber Building, 23/24 Russell Square Room: FG01
Type of Event: Seminar
Note: Internal event not open to external attendees.
Our world has a wealth of linguistic diversity, but many languages have yet to cross the "digital divide", with even technologies like smart keyboards with predictive text available in only a few hundred language varieties today. At Google, we've been working hard to bring language technology to more languages across the world: our Android keyboard now supports more than 500 language varieties, and we offer automatic speech recognition and machine translation for more than 100 language varieties. We'll talk about the research and practical challenges involved with building language technology across so many different languages, and we'll describe the important role of linguistic expertise in this process, covering how linguists, software engineers, and research scientists collaborate at Google (with room for Q&A for students interested in working in industry). Finally, we'll also briefly touch upon the potential of language technology to help accelerate language documentation work.
About the speakers:
Daan van Esch is a Technical Program Manager at Google. He works on internationalization for language technology at Google, harnessing machine learning and scalable infrastructure to bring support for new languages to products like Gboard and the Assistant. He's also working with the Centre of Excellence for the Dynamics of Language in Australia on applying automatic speech recognition technology in language documentation. Daan completed an MA in Chinese Studies from Leiden University in 2012, with a focus on Chinese linguistics.
Sandy Ritchie is an Analytical Linguist at Google. He works on speech recognition and text-to-speech systems, with a special focus on under-resourced languages. He completed the MA in Language Documentation and Description at SOAS in 2011, and the PhD in Linguistics in 2016. His published work to date explores possessive structures in Chimane (isolate, Bolivia) and Maithili (Indo-Aryan, India/Nepal).