Slav Petrov

I work on problems at the intersection of natural language processing and machine learning. I am particularly interested in multilingual syntactic analysis and its applications to machine translation and information extraction. Here is a video of a recent talk about my work, which has been recognized with best paper awards at NAACL 2012 and ACL 2011.

I completed my PhD at UC Berkeley in 2009, where I worked with Dan Klein. My Master's degree is from the Free University of Berlin, where our team won the RoboCup world championship in robotic soccer. I also spent a year as an exchange student at Duke University.

I grew up in Berlin, Germany, but I am originally from Sofia, Bulgaria. I therefore consider myself a Berliner from Bulgaria. Whenever Bulgaria plays Germany in soccer, I support Bulgaria.

See also my personal webpage for more information (including presentation slides).

Google Publications

Previous Publications

  •   

    Coarse-to-Fine Natural Language Processing

    Slav Petrov

    Ph.D. Thesis, University of California at Berkeley (2009)

  •   

    Coarse-to-Fine Syntactic Machine Translation using Language Projections

    Slav Petrov, Aria Haghighi, Dan Klein

    Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics, Honolulu, Hawaii, pp. 108-116

  •   

    Discriminative Log-Linear Grammars with Latent Variables

    Slav Petrov, Dan Klein

    Advances in Neural Information Processing Systems 20 (NIPS), MIT Press, Cambridge, MA (2008), pp. 1153-1160

  •   

    Efficient Sentence Segmentation Using Syntactic Features

    Benoit Favre, Dilek Hakkani-Tür, Slav Petrov, Dan Klein

    Spoken Language Technologies (SLT), Goa, India (2008)

  •   

    Parsing German with Latent Variable Grammars

    Slav Petrov, Dan Klein

    Proceedings of the Workshop on Parsing German at ACL '08, Association for Computational Linguistics, Columbus, Ohio (2008), pp. 33-39

  •   

    Sparse Multi-Scale Grammars for Discriminative Latent Variable Parsing

    Slav Petrov, Dan Klein

    Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics, Honolulu, Hawaii, pp. 867-876

  •   

    Improved Inference for Unlexicalized Parsing

    Slav Petrov, Dan Klein

    Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference, Association for Computational Linguistics, Rochester, New York, pp. 404-411

  •   

    Learning Structured Models for Phone Recognition

    Slav Petrov, Adam Pauls, Dan Klein

    Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 897-905

  •   

    Learning and Inference for Hierarchically Split PCFGs

    Slav Petrov, Dan Klein

    AAAI 2007 (Nectar Track)

  •   

    The Infinite PCFG Using Hierarchical Dirichlet Processes

    Percy Liang, Slav Petrov, Michael Jordan, Dan Klein

    Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 688-697

  •   

    Detecting Categories in News Video using Acoustic, Speech and Image Features

    Slav Petrov, Arlo Faria, Pascal Michaillat, Alexander Berg, Andreas Stolcke, Dan Klein, Jitendra Malik

    Proceedings of (VIDEO) TREC (TrecVid 2006)

  •   

    Learning Accurate, Compact, and Interpretable Tree Annotation

    Slav Petrov, Leon Barrett, Romain Thibaux, Dan Klein

    Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics (ACL/COLING), Association for Computational Linguistics, Sydney, Australia (2006), pp. 433-440

  •   

    Non-Local Modeling with a Mixture of PCFGs

    Slav Petrov, Leon Barrett, Dan Klein

    Proceedings of the Tenth Conference on Computational Natural Language Learning (CoNLL-X), Association for Computational Linguistics, New York City (2006), pp. 14-20

  •   

    3D Tracking = Classification + Interpolation

    Carlo Tomasi, Slav Petrov, Arvind Sastry

    Proceedings of the Ninth IEEE International Conference on Computer Vision (ICCV) (2003)