I'm a PhD Candidate working with Daniel Marcu in the Natural Language Group at the USC Information Sciences Institute. I am interested in getting machines to do useful things for us when it comes to human languages.

My focus has been to push the state-of-the-art in machine translation by marrying scalable and effective learning and inference with accurate syntactic models of word alignment. I also have many related interests, such as parallel text discovery, morphological modeling and generation, reordering and data visualization. Technical correspondence always welcome.

I successfully defended my thesis, Syntactic Alignment Models for Large-Scale Statistical Machine Translation, on March 21, 2012.

Syntactic Alignment Models for Large-Scale Statistical Machine Translation. Jason Riesa. PhD Thesis, University of Southern California. 2012.

Automatic Parallel Fragment Extraction from Noisy Data. Jason Riesa and Daniel Marcu. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT), 2012. [slides] [keynote] [code]

Feature-Rich Language-Independent Syntax-Based Alignment for Statistical Machine Translation. Jason Riesa, Ann Irvine, and Daniel Marcu. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2011. [slides] [keynote] [code]

Hierarchical Search for Word Alignment. Jason Riesa and Daniel Marcu. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL), 2010. [slides]

Minimally Supervised Morphological Segmentation with Applications to Machine Translation. Jason Riesa and David Yarowsky. In Proceedings of the 7th Conference of the Association for Machine Translation in the Americas (AMTA), 2006.

Building an English-Iraqi Arabic Machine Translation System for Spoken Utterances with Limited Resources. Jason Riesa, Behrang Mohit, Kevin Knight, Daniel Marcu. In Proceedings of Interspeech - ICSLP, 2006.

• How to talk like you're from Silicon Valley: Three rules to live by to fit in.
• For PhD Students: Three things they should have put in the manual (if there was a manual).

• Nile: A hierarchical syntax-based word alignment toolkit for statistical machine translation
• Picaro: A simple command-line word-alignment visualization tool
• Pyglog: A logging facility for Python.
• Alignment Visualization (web tool): A web-based version of Picaro.
• SBMT Rule Extraction (web tool): Visualize alignments and extract translation rules.

• Research Intern, Google Inc, Summer 2011.
• CSCI 562 - Empirical Methods in Natural Language Processing, Teaching Assistant, Fall 2010.
• NAACL HLT 2010, Los Angeles, Local Organizing Committee,
  with David Chiang, Ed Hovy, and Jonathan May.
• USC/ISI NL Seminar, Organizer, Fall 2009, Spring 2010, Summer 2010, Fall 2011, Spring 2012.
• USC/ISI NLP Reading Group, Organizer, Fall 2008, Spring 2009.
• 2nd Annual ISD Graduate Student Symposium, Co-Organizer,
  with Wes Kerr and Jonathan May.

MSE	2006	Johns Hopkins University	Computer Science
BS	2005	Johns Hopkins University	Computer Science
BS	2005	Johns Hopkins University	Applied Mathematics and Statistics