I am a postdoc with Christopher Manning at Stanford working on language modeling and machine translation. Recently, I completed a PhD advised by Alon Lavie at Carnegie Mellon and worked for Philipp Koehn at the University of Edinburgh.

My recent papers cover three areas:
Hypergraph search
 is a faster and more accurate alternative to cube pruning.
KenLM
 estimates and queries language models using less time and memory. It is behind three entries to the 2013 WMT evaluation, all of which won first place in their respective language pairs.
MEMT
 won best system combination in 8 of 10 tracks of the 2011 WMT evaluation.

I like travel, C++, math homework, and networking.