Sujith Ravi

Sujith Ravi is a Staff Research Scientist at Google. His main research interests span various problems and theory related to the fields of Natural Language Processing (NLP) and Machine Learning. He won the SIGKDD 2014 Best Research Paper Award and a Best Paper Award nomination at ACL 2009. He is specifically interested in large-scale unsupervised and semi-supervised methods and their applications to structured prediction problems in NLP, information extraction, multi-modal learning for language/vision, user modeling in social media, graph optimization algorithms for summarizing noisy data, computational decipherment and computational advertising. He is the founding member and technical lead of Google's large scale graph-based machine learning project which powers products in Search, Gmail, Photos, among others.

He completed his PhD at University of Southern California/Information Sciences Institute and was a Research Scientist at Yahoo! Research, Santa Clara before joining Google in Mountain View as a Research Scientist. Check his personal page for more information.

Google Publications

Previous Publications

  •   

    Revisiting the Predictability of Language: Response Completion in Social Media

    Bo Pang, Sujith Ravi

    Proceedings of the Conference on Empirical Methods in Natural Language Processing and Natural Language Learning (EMNLP-CoNLL) (2012)

  •   

    Bayesian Inference for Zodiac and Other Homophonic Ciphers

    Sujith Ravi, Kevin Knight

    Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT) (2011)

  •   

    Deciphering Foreign Language

    Sujith Ravi, Kevin Knight

    Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT) (2011)

  •   

    Semantic Role Labeling for CCG Without Treebanks

    Stephen Boxwell, Chris Brew, Jason Baldridge, Dennis Mehay, Sujith Ravi

    Proceedings of the International Joint Conference on Natural Language Processing (IJCNLP). (2011)

  •   

    Unsupervised Name Ambiguity Resolution Using A Generative Model

    Zornitsa Kozareva, Sujith Ravi

    Proceedings of the EMNLP Workshop on Unsupervised Learning in NLP (2011)

  •   

    Automatic generation of bid phrases for online advertising

    Sujith Ravi, Andrei Z. Broder, Evgeniy Gabrilovich, Vanja Josifovski, Sandeep Pandey, Bo Pang

    Proceedings of the International Conference on Web Search and Data Mining (WSDM) (2010), pp. 341-350

  •   

    Bayesian Inference for Finite-State Transducers

    David Chiang, Jonathan Graehl, Kevin Knight, Adam Pauls, Sujith Ravi

    Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL/HLT) (2010), pp. 447-455

  •   

    Does GIZA++ Make Search Errors?

    Sujith Ravi, Kevin Knight

    Computational Linguistics, vol. 36 (2010), pp. 295-302

  •   

    Fast, Greedy Model Minimization for Unsupervised Tagging

    Sujith Ravi, Ashish Vaswani, Kevin Knight, David Chiang

    Proceedings of the 23rd International Conference on Computational Linguistics (COLING) (2010), pp. 940-948

  •  

    Mining Student Discussions to Profile Participation and Scaffold Learning

    Jihie Kim, Erin Shaw, Sujith Ravi

    The Handbook of Educational Data Mining, CRC Press (2010), pp. 299-310

  •   

    A new objective function for word alignment

    Tugba Bodrumlu, Kevin Knight, Sujith Ravi

    Proceedings of the NAACL/HLT Workshop on Integer Programming for Natural Language Processing (2009), pp. 28-35

  •   

    Attacking Letter Substitution Ciphers with Integer Programming

    Sujith Ravi, Kevin Knight

    Cryptologia, vol. 33 (2009), pp. 321-334

  •   

    Learning phoneme mappings for transliteration without parallel data

    Sujith Ravi, Kevin Knight

    Proceedings of Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL/HLT) (2009), pp. 37-45

  •   

    Minimized models for unsupervised part-of-speech tagging

    Sujith Ravi, Kevin Knight

    Proceedings of the Joint Conferenceof the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing (ACL-IJCNLP) (2009), pp. 504-512

  •   

    Probabilistic Methods for a Japanese Syllable Cipher

    Sujith Ravi, Kevin Knight

    Proceedings of the 22nd International Conference on the Computer Processing of Oriental Languages (ICCPOL) (2009), pp. 270-281

  •   

    Attacking Decipherment Problems Optimally with Low-Order N-gram Models

    Sujith Ravi, Kevin Knight

    Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP) (2008), pp. 812-819

  •   

    Automatic Prediction of Parser Accuracy

    Sujith Ravi, Kevin Knight, Radu Soricut

    Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP) (2008), pp. 887-896

  •   

    Scaffolding On-Line Discussions with Past Discussions: An Analysis and Pilot Study of PedaBot

    Jihie Kim, Erin Shaw, Sujith Ravi, Erin Tavano, Aniwat Arromratana, Pankaj Sarda

    Proceedings of the 9th International Conference on Intelligent Tutoring Systems Conference (ITS) (2008), pp. 343-352

  •  

    Mining On-line Discussions: Assessing Technical Quality for Student Scaffolding and Classifying Messages for Participation Profiling

    Sujith Ravi, Jihie Kim, Erin Shaw

    Proceedings of the Educational Data Mining Workshop in the 13th International Conference on Artificial Intelligence in Education (AIED) (2007)

  •   

    Profiling Student Interactions in Threaded Discussions with Speech Act Classifiers

    Sujith Ravi, Jihie Kim

    Proceedings of the 13th International Conference on Artificial Intelligence in Education (AIED) (2007), pp. 357-364