Michael Denkowski

CV | GitHub | Google Scholar | CMU (snapshot)

michael.j.denkowski@gmail.com


I am a Senior Machine Learning Scientist at Amazon based in Fort Worth, Texas.


Publications

Bi-Directional Neural Machine Translation with Synthetic Parallel Data
Xing Niu; Michael Denkowski; Marine Carpuat
Proceedings of WNMT 2018
[bib]

The Sockeye Neural Machine Translation Toolkit at AMTA 2018
Felix Hieber; Tobias Domhan; Michael Denkowski; David Vilar; Artem Sokolov; Ann Clifton; Matt Post
Proceedings of AMTA 2018
[bib] [slides]

Stronger Baselines for Trustable Results in Neural Machine Translation
Michael Denkowski; Graham Neubig
Proceedings of WNMT 2017
[bib]

Machine Translation for Human Translators
Michael Denkowski
Ph.D. Thesis, Carnegie Mellon University, 2015
Committee: Alon Lavie; Chris Dyer; Jaime Carbonell; Gregory Shreve
[bib] [slides]

Cognitive Demand and Cognitive Effort in Post-Editing
Isabel Lacruz; Michael Denkowski; Alon Lavie
Proceedings of AMTA 2014
[bib]

Meteor Universal: Language Specific Translation Evaluation for Any Target Language
Michael Denkowski; Alon Lavie
Proceedings of WMT 2014
[bib] [poster]

Real Time Adaptive Machine Translation for Post-Editing with cdec and TransCenter
Michael Denkowski; Alon Lavie; Isabel Lacruz; Chris Dyer
Proceedings of HaCat 2014
[bib] [poster]

Learning from Post-Editing: Online Model Adaptation for Statistical Machine Translation
Michael Denkowski; Chris Dyer; Alon Lavie
Proceedings of EACL 2014
[bib] [poster]

Analyzing and Predicting MT Utility and Post-Editing Productivity in Enterprise-scale Translation Projects
Alon Lavie; Olga Beregovaya; Michael Denkowski; David Clarke
Proceedings of MT Summit 2013
[bib]

The CMU Machine Translation Systems at WMT 2013: Syntax, Synthetic Translation Options, and Pseudo-References
Waleed Ammar; Victor Chahuneau; Michael Denkowski; Greg Hanneman; Wang Ling; Austin Matthews; Kenton Murray; Nicola Segall; Alon Lavie; Chris Dyer
Proceedings of WMT 2013
[bib]

Challenges in Predicting Machine Translation Utility for Human Post-Editors
Michael Denkowski; Alon Lavie
Proceedings of AMTA 2012
[bib] [slides]

The CMU-Avenue French-English Translation System
Michael Denkowski; Greg Hanneman; Alon Lavie
Proceedings of WMT 2012
[bib]

Meteor 1.3 Automatic Metric for Reliable Optimization and Evaluation of Machine Translation Systems
Michael Denkowski; Alon Lavie
Proceedings of WMT 2011
[bib]

Choosing the Right Evaluation for Machine Translation: an Examination of Annotator and Automatic Metric Performance on Human Judgment Tasks
Michael Denkowski; Alon Lavie
Proceedings of AMTA 2010
[bib] [slides]

METEOR-NEXT and the METEOR Paraphrase Tables: Improved Evaluation Support For Five Target Languages
Michael Denkowski; Alon Lavie
Proceedings of WMT 2010
[bib]

Turker-Assisted Paraphrasing for English-Arabic Machine Translation
Michael Denkowski; Hassan Al-Haj; Alon Lavie
Proceedings of the CSLDAMT 2010
[bib]

Exploring Normalization Techniques for Human Judgments of Machine Translation Adequacy Collected Using Amazon Mechanical Turk
Michael Denkowski; Alon Lavie
Proceedings of the CSLDAMT 2010
[bib]

Extending the METEOR Machine Translation Evaluation Metric to the Phrase Level
Michael Denkowski; Alon Lavie
Proceedings of NAACL 2010
[bib]