Inhalt des Dokuments
|Slav Petrov (Google
7. Januar 2013, 13 Uhr, Gebäude Marchstraße 23, Raum MAR
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 recognition 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.
Slav Petrov is a Senior Research Scientist in Google's New York office. He works on problems at the intersection of natural language processing and machine learning. He is in particular interested in syntactic parsing and its applications to information extraction, question answering and machine translation. 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.