Picture of Matt Post
Matt Post
post @ cs . jhu . edu

I am a research scientist at the Johns Hopkins Human Language Technology Center of Excellence.

My main research interests are machine translation, syntax, parsing, and language modeling.

I maintain the Joshua decoder.

My publications, code and datasets, miscellaneous personal stuff.

Last spring, I taught a class on machine translation with Chris Callison-Burch and Adam Lopez.

2012

Findings of the 2012 Workshop on Statistical Machine Machine Translation. Chris Callison-Burch, Philipp Koehn, Christof Monz, Matt Post, Radu Soricut, and Lucia Specia. WMT. BIBTEX

Stylometric Analysis of Scientific Articles. Shane Bergsma, Matt Post, and David Yarowsky. NAACL. BIBTEX DATA

Constructing Parallel Corpora for Six Indian Languages via Crowdsourcing. Matt Post, Chris Callison-Burch and Miles Osborne. WMT. DATA BIBTEX SLIDES (KEY PDF PPT)

Joshua 4.0: Packing, PRO, and Paraphrasing. Juri Ganitkevitch, Yuan Cao, Jonny Weese, Matt Post, and Chris Callison-Burch. WMT. BIBTEX

Judging Grammaticality with Count-Induced Tree Substitution Grammars. Francis Ferraro, Matt Post, and Benjamin Van Durme. NAACL Workshop on Innovative Use of NLP for Building Educational Applications. BIBTEX

Toward Tree Substitution Grammars with Latent Annotations. Francis Ferraro, Benjamin Van Durme, and Matt Post. NAACL Workshop on Inducing Linguistic Structure. BIBTEX

2011

Joshua 3.0: Syntax-based Machine Translation with the Thrax Grammar Extractor. Jonathan Weese, Juri Ganitkevitch, Chris Callison-Burch, Matt Post and Adam Lopez. WMT. CODE

Judging Grammaticality with Tree Substitution Grammar Derivations. Matt Post. ACL (short paper). SLIDES DATA

2010

Ph.D. Thesis: Syntax-based Language Models for Statistical Machine Translation. University of Rochester Department of Computer Science. Advised by Dan Gildea.

Factors affecting the accuracy of Korean parsing. Tagyoung Chung, Matt Post, and Daniel Gildea. NAACL Workshop on Statistical Parsing of Morphologically Rich Languages.

Word Production in Spontaneous Speech: Availability and Communicative Efficiency. T. Florian Jaeger and Matt Post. Conference on Human Sentence Processing.

2009

Language modeling with tree substitution grammars. Matt Post and Daniel Gildea. NIPS workshop on Grammar Induction, Representation of Language, and Language Learning.

Weight pushing and binarization for fixed-grammar parsing. Matt Post and Daniel Gildea. IWPT. SLIDES BIBTEX

Bayesian learning of a tree substitution grammar. Matt Post and Daniel Gildea. ACL (short paper). POSTER BIBTEX CODE

2008

Parsers as language models for statistical machine translation. Matt Post and Daniel Gildea. AMTA. SLIDES BIBTEX (code available upon request.)

The Web as a Psycholinguistic Resource. Austin F. Frank, Celeste Kidd, Matthew Post, Benjamin Van Durme and T. Florian Jaeger. International Workshop on Language Production.

2004

Myriad: An Architecture for Contextualized Information Retrieval and Delivery. Cecile Paris, MingFang Wu, Keith Vander Linden, Matthew Post, and Shijian Lu. International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems. BIBTEX