Steve DeNeefe

Update: I've graduated and now work at SDL Language Weaver in Los Angeles as a research scientist with their Automated Translation team. Please contact me at my gmail or sdl.com address (both sdeneefe).

I'm a graduate student in Computer Science at University of Southern California's Information Sciences Institute. I started the program in Fall of 2003, after working as a software developer at ESRI for about seven years. I am interested in using computers for translation between different human languages, and languages in general (both human languages and computer languages). My advisor is Kevin Knight.

Publications:

• Steve DeNeefe, Kevin Knight, Hayward H. Chan. Interactively Exploring a Machine Translation Model. Interactive Poster/Demonstration, Companion Volume to the Proceedings of the Association for Computational Linguistics (ACL). June 25, 2005. Ann Arbor, Michigan.
• Michel Galley, Jonathan Graehl, Kevin Knight, Daniel Marcu, Steve DeNeefe, Wei Wang, Ignacio Thayer. Scalable Inference and Training of Context-Rich Syntactic Translation Models. Proceedings of the Joint Conference of the International Committee on Computational Linguistics and the Association for Computational Linguistics (COLING/ACL). July 17-21, 2006. Sydney, Australia.
• Steve DeNeefe, Kevin Knight, Wei Wang, Daniel Marcu. What Can Syntax-Based MT Learn from Phrase-Based MT? Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL). June 28-30, 2007. Prague, Czech Republic. (slides: PDF, ODF presentation)
• Steve DeNeefe, Ulf Hermjakob, Kevin Knight. Overcoming Vocabulary Sparsity in MT Using Lattices. Proceedings of the Eighth Conference of the Association for Machine Translation in the Americas (AMTA). October 21-25, 2008. Waikiki, Hawaii.
• David Chiang, Steve DeNeefe, Yee Seng Chan, Hwee Tou Ng. Decomposability of translation metrics for improved evaluation and efficient algorithms. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2008). October 25-27, 2008. Waikiki, Hawaii.
• Steve DeNeefe, Kevin Knight. Synchronous Tree Adjoining Machine Translation. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). August 6-7, 2009. Singapore.
• Steve DeNeefe, Kevin Knight and Heiko Vogler. A Decoder for Probabilistic Synchronous Tree Insertion Grammars. Proceedings of the Workshop on Applications of Tree Automata in Natural Language Processing (ATANLP). July 16, 2010. Uppsala, Sweden.
• Steve DeNeefe, Libin Shen, Kevin Knight, Daniel Marcu, Wei Wang, Ralph Weischedel, Jinxi Xu. Two String-to-Tree Translation Models. To appear in Handbook of Natural Language Processing and Machine Translation: DARPA Global Autonomous Language Exploitation. Eds. Joseph Olive, Caitlin Christianson, John McCary.
• David Chiang, Steve DeNeefe, and Michael Pust. Two easy improvements to lexical weighting. Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT) June 19-24, 2011. Portland, Oregon.

Doctoral Thesis:

• Read my thesis proposal (date proposed: October 30, 2009) or the completed thesis (date defended: October 11, 2011). I'd love your feedback.

Recent Activities:

• Participation in NIST MT Evaluations 2006 - 2009
• Participation in GALE MT Evaluations 2007 - 2008