Chris Dyer's Homepage

I'm a postdoc in the Language Technologies Institute in the School of Computer Science at CMU, working with Noah, in the ARK.

Prior to coming here, I did a PhD in linguistics at the University of Maryland, working with Philip Resnik. I am both a computer scientist and a linguist.

My research interests lie at the intersection of machine learning, natural language processing, and linguistics. I like learning from data, and I do a lot of work on machine translation.

Current events

Together with Alan W. Black, I'm teaching Natural Language Processing (registered students only).
I'm applying for jobs! Are you hiring? Here's my CV.
Together with Chris Quirk and Adrià de Gispert, I'm area chair for the machine translation track at EMNLP/CoNLL 2012.

Publications

A. Levenberg, C. Dyer, and P. Blunsom. A Bayesian Model for Learning SCFGs with Discontiguous Rules. To appear in Proceedings of EMNLP. 2012.

P. Simianer, C. Dyer, and S. Riezler. Joint Feature Selection in Distributed Stochastic Learning for Large-Scale Discriminative Training in SMT. To appear in Proceedings of ACL. 2012.

W. Ammar, C. Dyer, and N. A. Smith. Transliteration by Sequence Labeling with Lattice Encodings and Reranking. To appear in Proceedings of the NEWS Workshop at ACL. 2012.

K. M. Hermann, C. Dyer, P. Blunsom, and S. Pulman. Learning Semantics and Selectional Preference of Adjective-Noun Pairs. To appear in Proceedings of *SEM. 2012.

D. Yogatama, M. Heilman, B. O'Connor, C. Dyer, B. Routledge, and N. A. Smith. Predicting a Scientific Community's Response to an Article. In Proceedings of EMNLP. 2011.

D. Chen, C. Dyer, S. B. Cohen, and N. A. Smith. Unsupervised Bilingual POS Tagging with Markov Random Fields. In Proceedings of the First Workshop on Unsupervised Learning in NLP. 2011.

C. Dyer, K. Gimpel, J. H. Clark, and N. A. Smith. The CMU-ARK German-English Translation System. In Proceedings of the Sixth Workshop on Machine Translation (WMT11). 2011. Humans like us!

J. H. Clark, C. Dyer, A. Lavie, and N. A. Smith. Better Hypothesis Testing for Machine Translation: Controlling for Optimizer Instability. In Proceedings of ACL. 2011. [software]

C. Dyer, J. H. Clark, A. Lavie, and N. A. Smith. Unsupervised Word Alignment with Arbitrary Features. In Proceedings of ACL. 2011. [software] [Keynote slides]

A. Arun, B. Haddow, P. Koehn, A. Lopez, C. Dyer, and P. Blunsom. Monte Carlo techniques for phrase-based translation. In Machine Translation 24(2):103-121, 2010.

H. Setiawan, C. Dyer, and P. Resnik. Discriminative Word Alignment with a Function Word Reordering Model. In Proceedings of EMNLP. 2010.

V. Eidelman, C. Dyer, and P. Resnik. The University of Maryland statistical machine translation system for the Fifth Workshop on Machine Translation. In Proceedings of the Association for Computational Linguistics (ACL) Joint Fifth Workshop on Statistical Machine Translation and Metrics MATR. 2010.

C. Dyer, A. Lopez, J. Ganitkevitch, J. Weese, F. Ture, P. Blunsom, H. Setiawan, V. Eidelman, and P. Resnik. cdec: A Decoder, Alignment, and Learning Framework for Finite-State and Context-Free Translation Models. In Proceedings of ACL (Demonstration track), 2010. [software]

C. Dyer. A Formal Model of Ambiguity and its Applications in Machine Translation. Dissertation, University of Maryland. 2010. [software]

J. Lin and C. Dyer. Data-Intensive Text Processing with MapReduce. Ed. Graeme Hirst. Morgan and Claypool Publishers. 2010. [Amazon.com].

C. Dyer and P. Resnik. Context-free reordering, finite-state translation. In Proceedings of NAACL-HLT 2010, Los Angeles, CA, USA, 2010. [Keynote slides] [PDF slides] [software]

C. Dyer. Two monolignual parses are better than one (synchronous parse). In Proceedings of NAACL-HLT 2010, Los Angeles, CA, USA, 2010. [software]

P. Blunsom, T. Cohn, C. Dyer, and M. Osborne. A Gibbs sampler for phrasal synchronous grammar induction. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), Singapore, August 2009.

S. Kumar, W. Macherey, C. Dyer, and F. Och. Efficient minimum error rate training and minimum Bayes-risk decoding for translation hypergraphs and lattices. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), Singapore, August 2009.

C. Dyer. Using a maximum entropy model to build segmentation lattices for MT. In Proceedings of NAACL HLT 2009, Boulder, Colorado, June 2009. [slides] [software] Note: see chapter 4 of my thesis for a much better explanation of this work.

A. Arun, C. Dyer, P. Blunsom, B. Haddow, A. Lopez, and P. Koehn. Monte Carlo inference and maximization for phrase-based translation. In Proceedings of CoNLL, Boulder, Colorado, June 2009.

C. Dyer, H. Setiawan, Y. Marton, and P. Resnik. The University of Maryland Statistical Machine Translation System for the Third Workshop on Machine Translation. In Proceedings of the EACL-2009 Workshop on Statistical Machine Translation (WMT-2009), Athens, Greece, March 2009.

Z. Li, C. Callison-Burch, C. Dyer, J. Ganitkevitch, S. Khudanpur, L. Schwartz, W. Thornton, J. Weese, and O. Zaidan. 2009. Joshua: Open Source Toolkit for Parsing-based Machine Translation. In EACL 2009 Fourth Workshop on Statistical Machine Translation, Athens, Greece, March 2009.

C. Dyer, A. Cordova, A. Mont, and J. Lin. Fast, Cheap, and Easy: Construction of Statistical Machine Translation Models with MapReduce. In Proceedings of the ACL-2008 Workshop on Statistical Machine Translation (WMT-2008), Columbus, Ohio, July 2008.

C. Dyer, S. Muresan, and P. Resnik. Generalizing Word Lattice Translation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), Columbus, Ohio, July 2008.

C. Dyer. The University of Maryland Translation System for IWSLT 2007. In Proceedings of the International Workshop on Spoken Language Translation (IWSLT) 2007, Trento, Italy, October 2007.

C. Dyer. The 'noiser channel': Translation from morphologically complex languages. In Proceedings of the ACL-2007 Workshop on Statistical Machine Translation (WMT-2007), Prague, Czech Republic, June 2007.

P. Koehn, H. Hoang, A. Birch, C. Callison-Burch, M. Federico, N. Bertoldi, B. Cowan, W. Shen, C. Moran, R. Zens, C. Dyer, O. Bojar, A. Constantin and E. Herbst. Moses: Open Source Toolkit for Statistical Machine Translation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), Companion Volume, Prague, Czech Republic, June 2007.

A. Omaki, C. Dyer, S. Malhotra, J. Sprouse, J. Lidz, & C. Phillips. The time-course of anaphoric processing and syntactic reconstruction. Presented at CUNY 2007, San Diego, March 2007.

Various talks

C. Dyer. Introduction to Statistical Machine Translation. Lecture given at the 2011 JHU Summer School on Human Language Technology, July 2011.

C. Dyer. Integrating Morphology in Probabilistic Translation Models. Invited talk presented at the Workshop on Machine Translation and Morphologically-rich Languages, Haifa, Israel.

C. Dyer. Scaling NLP and MT with MapReduce. Presented at Raytheon BBN Technologies, Cambridge, MA, November, 2010.

J. Lin and C. Dyer. Data-Intensive Text Processing with MapReduce. Tutorial presented at the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT) 2010 Conference.

C. Dyer. Introduction to Syntactic Machine Translation. Presented at the Machine Translation Marathon, Dublin, January 2010.

C. Dyer. Improving machine translation by propagating uncertainty. Presented at IBM TJ Watson Research Center, The Center for Language and Speech Processing at JHU, and the Language Technology Institute at CMU, August 2009.

Software and data

creg is a fast and small regression package.
Here is a Korean-English Wikipedia titles corpus from January 2012.
I prepared a corpus of child-directed German for a paper I wrote in graduate school on word segmentation/lexicon induction. It is similar in size, complexity, and content (in terms of the age of the child) to the widely used Brent/Bernstein-Ratner corpus. Contact me if you intend to publish a paper using this data!
cdec is the decoder I wrote during my thesis work for statistical machine translation and other structured prediction models. If I wrote a paper about it, there's a good chance the code is here.
libpopt is a small, fast C++ library that implements a few gradient-based optimization algorithms (LBFGS, stochastic gradient descent, Rprop) where the optimizer's state can be persisted between function evaluations. This makes it possible to perform successive optimization iterations in different processes or on different machines (useful with MapReduce).
In a fit of rage and frustration that no such tool existed, I wrote a very small, very fast Chinese word segmenter that's in C++.
GIZA++ and MkCls, "fixed" to compile with recent GCCs.
A Java implementation of the Buckwalter Morphological Analyzer v1 (GPL License, data (c) 2001 by the LDC).
Chinese place names (Chinese (utf-8) | English) which were mined from some huge lists at Wikipedia (URL list).

Random things

Like all good things, coauthorship frequency ~~follows a power law~~ has a long tail.