The biggest barrier to global communication is the fact that we speak many different languages. My research focuses on technology that will break this barrier, in particular systems that learn to translate from big data (like Google Translate, Bing Translator, and SDL Free Translation), and their integration with speech and search technologies. Improvements to these systems depend on extensions and applications of machine learning, formal language theory, linguistics, and algorithms. I am interested in many problems in these fields.


Selected Papers

Gappy pattern matching on GPUs for on-demand extraction of hierarchical translation grammars
Hua He, Jimmy Lin, and Adam Lopez. In Transactions of the ACL, 3 2015.
Abstract Code
Dirt Cheap Web-Scale Parallel Text from the Common Crawl
Jason Smith, Herve Saint-Amand, Magdalena Plamada, Philipp Koehn, Chris Callison-Burch and Adam Lopez. In Proceedings of ACL, 2013.
Abstract Code
Learning to translate with products of novices: a suite of open-ended challenge problems for teaching MT
With Matt Post, Chris Callison-Burch, Jonathan Weese, Juri Ganitkevitch, Narges Ahmidi, Olivia Buzek, Leah Hanson, Beenish Jamil, Matthias Lee, Ya-Ting Lin, Henry Pao, Fatima Rivera, Leili Shahriyari, Debu Sinha, Adam Teichert, Stephen Wampler, Michael Weinberger, Daguang Xu, Lin Yang, and Shang Zhao. In Transactions of the ACL, 1 : pages 165–178, 2013.
Abstract Code
Training a Log-Linear Parser with Loss Functions via Softmax-Margin
Michael Auli and Adam Lopez. In Proceedings of EMNLP, 2011.
A Comparison of Loopy Belief Propagation and Dual Decomposition for Integrated CCG Supertagging and Parsing
Michael Auli and Adam Lopez. In Proceedings of ACL, 2011.