Type of Talk: UTCS Corporate Connection

Speaker/Affiliation: Slav Petrov/Google Research Scientist

Talk Audience: UTCS Graduate Students

Date/Time: Friday, September 28, 2012, 2:30 - 3:30 pm

Location: ACES 2.302

Host: FoCS Talk

Title: Understanding all the World's Languages

Talk Abstract:
The impact of computer systems that can understand natural language will be tremendous. To develop this capability we need to be able to automatically and efficiently analyze large amounts of text. In the last twenty years, the statistical revolution has brought tremendous progress, enabling us to build systems for speech recogn ition and machine translation that perform impressively well and are used by millions of people every day. In this talk, I will review some current challenges and success stories, and give an outlook of what might be waiting for us in the future. Particular attention will be paid to how the goal of understanding all the world's languages involves challenges in all areas of Computer Science because of its scale and ambition.

RSVP at bit.ly/UTGRAD

Bio:
Slav Petrov is a Senior Research Scientist in Google's New York office. He wor ks on problems at the intersection of natural language processing and machine learning. He is in particular interested in syntactic parsing and its ap plications to information extraction, question answering and machine trans lation. Prior to Google, Slav completed his PhD degree at UC Berkeley, where he worked with Dan Klein. He holds a Master's degree from the Free University of Berlin and was a member of the FU-Fighters team that won the RoboCup world championship in 2004. His work on fast and accurate multilingual syntactic analysis has recently been recognized with best paper awards at ACL 2011 and NAACL 2012. Slav also teaches a class on Statistical Natural Language Processing at New York University.