publications

Click on paper titles to see their abstracts.

2016

Automatic Construction of Morphologically Motivated Translation Models for Highly Inflected, Low-Resource Languages (Proceedings of AMTA 2016) | John Hewitt, Matt Post and David Yarowsky PDF
Findings of the 2016 Conference on Machine Translation (Proceedings of the First Conference on Machine Translation) | Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Varvara Logacheva, Christof Monz, Matteo Negri, Aurelie Neveol, Mariana Neves, Martin Popel, Matt Post, Raphael Rubino, Carolina Scarton, Lucia Specia, Marco Turchi, Karin Verspoor and Marcos Zampieri PDF
Syntax-based Statistical Machine Translation (Synthesis Lectures on Human Language Technologies) | Philip Williams, Rico Sennrich, Matt Post and Philipp Koehn PDF
Sentential Paraphrasing as Black-Box Machine Translation (NAACL Demo Track) | Courtney Napoles, Chris Callison-Burch and Matt Post PDF
Reassessing the Goals of Grammatical Error Correction: Fluency Instead of Grammaticality (Transactions of the Association for Computational Linguistics) | Keisuke Sakaguchi, Courtney Napoles, Matt Post and Joel Tetreault PDF
Ten Years of WMT Evaluation Campaigns: Lessons Learnt (Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)) | Ondřej Bojar, Christian Federmann, Barry Haddow, Philipp Koehn, Matt Post and Lucia Specia PDF

2015

A Universal Feature Schema for Rich Morphological Annotation and Fine-Grained Cross-Lingual Part-of- Speech Tagging (Springer (book chapter)) | John Sylak-Glassman and Christo Kirov and Matt Post and Roger Que and David Yarowsky
Joshua 6: A phrase-based and hierarchical statistical machine translation system (Prague Bulletin of Mathematical Linguistics) | Matt Post and Yuan Cao and Gaurav Kumar PDF Data

2015

Findings of the 2015 Workshop on Statistical Machine Translation (Proceedings of the Tenth Workshop on Statistical Machine Translation) | Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Barry Haddow, Matthias Huck, Chris Hokamp, Philipp Koehn, Varvara Logacheva, Christof Monz, Matteo Negri, Matt Post, Carolina Scarton, Lucia Specia and Marco Turchi PDF

2015

Ground Truth for Grammaticality Correction Metrics (ACL) | Courtney Napoles and Keisuke Sakaguchi and Matt Post and Joel Tetreault PDF Data

2014

The Machine Translation Leaderboard (Prague Bulletin of Mathematical Linguistics) | Matt Post and Adam Lopez PDF Data
Findings of the 2014 Workshop on Statistical Machine Translation (WMT14) | Ondrej Bojar, Christian Buck, Christian Federmann, Barry Haddow, Philipp Koehn, Johannes Leveling, Christof Monz, Pavel Pecina, Matt Post, Herve Saint-Amand, Radu Soricut, Lucia Specia, and Aleš Tamchyna PDF Data
Efficient Elicitation of Annotations for Human Evaluation of Machine Translation (WMT14) | Keisuke Sakaguchi, Matt Post, and Benjamin Van Durme PDF Data
A Wikipedia-based Corpus for Contextualized Machine Translation. (LREC) | Jennifer Drexler, Pushpendre Rastogi, Jacqueline Aguilar, Benjamin Van Durme, and Matt Post PDF
Some Insights from Translating Conversational Telephone Speech (ICASSP) | Gaurav Kumar, Matt Post, Daniel Povey, and Sanjeev Khudanpur PDF
The Language Demographics of Amazon Mechanical Turk (TACL) | Ellie Pavlick, Matt Post, Ann Irvine, Dmitry Kachaev, and Chris Callison-Burch PDF

2013

Improved Speech-to-Text Translation with the Fisher and Callhome Spanish--English Speech Translation Corpus (IWSLT) | Matt Post, Gaurav Kumar, Adam Lopez, Damianos Karakos, Chris Callison-Burch and Sanjeev Khudanpur PDF Data
Beyond Bitext: Five open problems in machine translation (EMNLP Workshop on Twenty Years of Bitext) | Adam Lopez and Matt Post PDF
Bayesian Tree Substitution Grammars as a Usage-Based Approach (Language and Speech) | Matt Post and Daniel Gildea PDF
Joshua 5.0: Sparser, Better, Faster, Server (WMT) | Matt Post, Juri Ganitkevitch, Luke Orland, Jonathan Weese, Yuan Cao and Chris Callison-Burch PDF Data
Findings of the 2013 Workshop on Statistical Machine Translation (WMT) | Ondřej Bojar, Christian Buck, Chris Callison-Burch, Christian Federmann, Barry Haddow, Philipp Koehn, Christof Monz, Matt Post, Radu Soricut and Lucia Specia PDF Data
Explicit and Implicit Syntactic Features for Text Classification (ACL) | Matt Post and Shane Bergsma PDF Data
Learning to translate with products of novices: a suite of open-ended challenge problems for teaching MT (TACL) | Adam Lopez, Matt Post, Chris Callison-Burch, Jonathan Weese, Juri Ganitkevitch, Narges Ahmidi, Olivia Buzek, Leah Hanson, Beenish Jamil, Matthias Lee and others PDF Data

2012

Toward Tree Substitution Grammars with Latent Annotations (NAACL-HLT Workshop on the Induction of Linguistic Structure) | Francis Ferraro, Benjamin Van Durme, and Matt Post PDF
Judging Grammaticality with Count-Induced Tree Substitution Grammars (NAACL-HLT Workshop on Innovative Use of NLP for Building Educational Applications) | Francis Ferraro, Matt Post, and Benjamin Van Durme PDF Data
Constructing Parallel Corpora for Six Indian Languages via Crowdsourcing (WMT) | Matt Post, Chris Callison-Burch and Miles Osborne PDF Data
Joshua 4.0: Packing, PRO, and paraphrases (WMT) | J. Ganitkevitch, Y. Cao, J. Weese, M. Post and C. Callison-Burch PDF
Findings of the 2012 Workshop on Statistical Machine Translation (WMT) | Chris Callison-Burch, Philipp Koehn, Christof Monz, Matt Post, Radu Soricut and Lucia Specia PDF Data
Stylometric Analysis of Scientific Articles (NAACL-HLT) | Shane Bergsma, Matt Post and David Yarowsky PDF Data

2011

Joshua 3.0: Syntax-based machine translation with the thrax grammar extractor (WMT) | Jonathan Weese, Juri Ganitkevitch, Chris Callison-Burch, Matt Post and Adam Lopez PDF Data
Judging Grammaticality with Tree Substitution Grammar Derivations (ACL) | Matt Post PDF Data

2010

Syntax-based Language Models for Statistical Machine Translation (PhD Thesis, University of Rochester) | Matt Post
Word Production in Spontaneous Speech: Availability and Communicative Efficiency (Conference on Human Sentence Processing) | T. Florian Jaeger and Matt Post
Factors Affecting the Accuracy of Korean Parsing (NAACL-HLT Workshop on Statistical Parsing of Morphologically-Rich Languages) | Tagyoung Chung, Matt Post and Daniel Gildea PDF

2009

Weight Pushing and Binarization for Fixed-Grammar Parsing (IWPT) | Matt Post and Daniel Gildea PDF Data
Language modeling with tree substitution grammars (NIPS workshop on Grammar Induction, Representation of Language, and Language Learning) | Matt Post and Daniel Gildea PDF
Bayesian learning of a tree substitution grammar (ACL) | Matt Post and Daniel Gildea PDF

2008

The Web as a Psycholinguistic Resource (International Workshop on Language Production) | Austin F. Frank, Celeste Kidd, Matthew Post, Benjamin Van Durme and T. Florian Jaeger
Parsers as language models for statistical machine translation (AMTA) | Matt Post and Daniel Gildea PDF

2004

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