Adam Lopez

Biography

I am a postdoctoral research fellow working with Philipp Koehn on statistical machine translation. I earned my Ph.D. in computer science at the University of Maryland, where I worked with Philip Resnik. Prior to graduate school, I was a software engineer at IBM, and prior to that I studied computer science at Duke University. I did not work with anyone named Philip at these earlier places.

Publications

Statistical Machine Translation. In ACM Computing Surveys 40(3), article 8, pp. 1—49, August 2008.

Tera-Scale Translation Models via Pattern Matching. In Proceedings of COLING, pp. 505—512, August 2008. [slides]

Machine Translation by Pattern Matching. Dissertation, University of Maryland, March 2008. [official page] [LaTeX source] [slides]

Hierarchical Phrase-Based Translation with Suffix Arrays. In Proceedings of EMNLP-CoNLL, pp. 976—985, June 2007. [slides]

Word-Based Alignment, Phrase-Based Translation: What's the Link? with Philip Resnik. In Proceedings of AMTA, pp. 90—99. August 2006. [slides]

The Hiero Machine Translation System: Extensions, Evaluation, and Analysis. David Chiang, Adam Lopez, Nitin Madnani, Christof Monz, Philip Resnik, and Michael Subotin. In Proceedings of HLT/EMNLP, pp. 779—786. October 2005. [slides]

Pattern Visualization for Machine Translation Output. with Philip Resnik. In Proceedings of HLT/EMNLP Demonstrations, pp. 12—13. October 2005. [slides]

Improved HMM Alignment Models for Languages with Scarce Resources. with Philip Resnik. In Proceedings of the ACL 2005 Workshop on Building and Using Parallel Texts: Data Driven Machine Translation and Beyond, pp. 83—86. June 2005.

Word-Level Alignment for Multilingual Resource Acquisition. with Michael Nossal, Rebecca Hwa, and Philip Resnik. In Proceedings of the LREC Workshop on Linguistic Knowledge Acquisition and Representation – Bootstrapping Annotated Language Data, pp. 34—42. May 2002. [slides]

Talks and Tutorials

Over the last few years I have come around to the view that slides are visual aids for talks, so I make no representation that they stand on their own without an accompanying narration. (At least the later ones. Some of the earlier ones contain complete sentences.) Even so, I occasionally get requests for them. Here they are.

Translation by Pattern Matching. Invited talk at Second MT Marathon, May 2008.

Syntax-Based Machine Translation. Class lecture at Second MT Marathon, May 2008.

Hierarchical Phrase-Based Translation with Suffix Arrays. Invited talk given at between February and July, 2007 at the University of Edinburgh, Microsoft Research, Carnegie Mellon University, University of Pittsburgh, University of Amsterdam, and the MITRE Corporation.

How Does Machine Translation Work? Guest lecture in Transformational Technologies class at the University of Maryland, April 2007. This talk is aimed at students outside of NLP who have no exposure to the mechanics of machine translation. It's a fun talk, and I'd be happy to present it at your university. Earlier versions:

Translation by the Numbers. Invited talk at Colgate University, October 2006.

Statistical Machine Translation. Invited talk at Union College, September 2005.

Inside the Hiero Decoder. Tutorial given at the University of Maryland, September 2006.

Software

Extensions to David Chiang's Hiero that support translation by pattern matching. Email me for details.

Gene Chipman and I once wrote a program that plays a decent game of checkers.