Mehryar Mohri

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search

Mehryar Mohri is a professor of computer science at the Courant Institute of Mathematical Sciences at New York University known for his work in machine learning, automata theory and algorithms, speech recognition and natural language processing. He is also an Engineering Director at Google and heads the Learning Theory team at Google Research.

He received his B.S from École Polytechnique (1987), his M.S. in computer science and applied mathematics from École Normale Supérieure (1989) and his Ph.D. in 1993 from the University of Paris 7 Denis Diderot.[1] Prior to joining the Courant Institute in 2004, Mohri worked for ten years at Bell Labs and AT&T Labs, where he was Head of the Speech Algorithms Department.[2]

Mohri's main areas of research are machine learning, theory, computational biology, and text and speech processing.[3] He is the author of many core weighted automata and finite state transducer algorithms and pioneered the application of weighted finite state transducers (WFSTs) to speech recognition and natural language processing with his colleagues at AT&T.[4]

At the Eurospeech 2001 conference in Aalborg, a paper by Mohri and Michael Riley, “Network Optimizations for Large-Vocabulary Speech Recognition,” was given an award by the International Speech Communication Association as “the best paper published in Speech Communications during 1998-2000.”[5] His work with Brian Roark, “Probabilistic Context-Free Grammar Induction Based on Structural Zeros,” won a best paper award at HLT-NAACL 2006.[6] Mohri is Editorial Board member of Machine Learning[7] and member of the advisory board for the Journal of Automata, Languages and Combinatorics.[8]