Igor Malioutov


The Stata Center
32 Vassar Street, Room 32-G360
Cambridge, MA 02139
USA 

About Me

I am a PhD student at the MIT CSAIL laboratory, co-advised by Professor Robert Berwick and Professor Whitman Richards. My interests include formal linguistics and unsupervised learning techniques for natural language syntax and semantics. I am currently working on developing new computational formalisms for grammar induction with my advisors and Prof. Sandiway Fong from the Department of Linguistics and Computer Science at the University of Arizona.

I am a National Science Foundation Graduate Research Fellow. For my Master's thesis, I developed state-of-the-art models for unsupervised spoken lecture segmentation under the supervision of Prof. Regina Barzilay. During the summer of 2007, I was advised by Kristina Toutanova as part of my research internship at the Microsoft Research Natural Language Processing group. During the Fall 2007 semester, I was the Teaching Assistant for 6.864: Advanced Natural Language Processing, taught by Prof. Michael Collins.

Patents

Igor Malioutov, Alex Park. Unsupervised Topic Segmentation of Acoustic Speech Signal. USPTO ID 20090132252.

Publications

Igor Malioutov, Alex Park, Regina Barzilay, and James Glass. Making Sense of Sound: Unsupervised Topic Segmentation over Acoustic Input.In Proceedings of ACL, 2007. [bib]

James Glass, Timothy J. Hazen, Scott Cyphers, Igor Malioutov, David Huynh, and Regina Barzilay. Recent Progress in the MIT Spoken Lecture Processing Project. In Proceedings of INTERSPEECH, 2007.

Igor Malioutov. Minimum Cut Model for Spoken Lecture Segmentation. Master's Thesis. MIT, 2006.

Igor Malioutov, Regina Barzilay. Minimum Cut Model for Spoken Lecture Segmentation. In Proceedings of COLING-ACL 2006, pp. 9-16. [bib] [materials][code]

Gene Cooperman, Viet Ha Nguyen, Igor Malioutov. Parallelization of Geant4 Using TOP-C and Marshalgen. IEEE NCA, 2006. [bib]

Andrew L. Rukhin, Igor Malioutov. Fusion of biometric algorithms in the recognition problem. Pattern Recognition Letters 26(5): 679-684 (2005). [bib]

Contact

i go r m AT csail.mit.edu