Home
CV
Publications
Design
Pictures
2009

Kevin Gimpel and Noah A. Smith. Feature-Rich Translation by Quasi-Synchronous Lattice Parsing. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Singapore, August 2009.
[paper] [slides]

Kevin Gimpel and Noah A. Smith. Cube Summing, Approximate Inference with Non-Local Features, and Dynamic Programming without Semirings. In Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics (EACL), Athens, Greece, March/April 2009.
[paper] [slides]

2008

Shay B. Cohen, Kevin Gimpel, and Noah A. Smith. Logistic Normal Priors for Unsupervised Probabilistic Grammar Induction. In Advances in Neural Information Processing Systems (NIPS) 21.
[paper] [code]

Kevin Gimpel and Noah A. Smith. Rich Source-Side Context for Statistical Machine Translation. In Proceedings of the ACL-2008 Workshop on Statistical Machine Translation (WMT-2008), Columbus, OH, June 2008.
[paper] [code for significance testing]


Work done at MIT Lincoln Laboratory:

K. Gimpel and D. Rudoy. Statistical Inference in Graphical Models. MIT Lincoln Laboratory Technical Report TR-1115, 2006.

K. O’Grady, S. Uftring, N. Arcolano, and K. Gimpel. Live-Time Discrimination Experiments Using Data Fused Across Multiple Missile Phases. Proceedings of the 2006 Meeting of the Military Sensing Symposia (MSS) on Missile Defense Sensors, Environments, and Algorithms (MD-SEA), Naval Post Graduate School, Monterey, CA 24-26 October 2006.


Other Papers/Presentations (unpublished):

Discriminative Online Algorithms for Sequence Labeling - A Comparative Study. With Shay Cohen, Course Project for Information Extraction, 2007.

Modeling Topics. Literature review on topic modeling for Language and Statistics II, 2006.

Beating the NFL Football Point Spread. Course project report for Machine Learning, 2006. If you're interested in the data I used, check out my brother's company.

Notes on graphical models

Junction Tree Algorithms for Inference in Dynamic Bayesian Networks