Speaker: Spence Green
In this talk we'll describe recent progress in interactive neural machine translation, which is a human-in-the-loop machine learning task. First, we'll motivate interactive MT, which is an idea that dates to the 1960s that has only recently been realized in commercially available systems. Next, we'll describe recent research results and what they mean for domain adaptation, inference, and word alignment. Finally, I'll offer some brief reflections on doing research in a startup setting.
No webcast/livestream or recording. Please join us in person!
6:30-7:00 pm Networking and snacks
7:00-8:30 pm Presentation and discussion
8:30-9:00 pm Social time, extended Q&A
Spence Green is the CEO at Lilt, a San Francisco-based startup that builds intelligent software to automate translation for businesses. Spence graduated from Stanford with a PhD in computer science. His research area focused on the intersection of natural language processing and human-computer interaction. He has published papers on statistical machine translation, statistical language parsing, and mixed-initiative systems and given talks on translator productivity.