The AFRL-MITLL WMT15 System: There's More than One Way to Decode It!

Abstract

This paper describes the AFRL-MITLL statistical MT systems and the improvements that were developed during the WMT15 evaluation campaign. As part of these efforts we experimented with a number of extensions to the standard phrasebased model that improve performance on the Russian to English translation task creating three submission systems with different decoding strategies. Out of vocabulary words were addressed with named entity postprocessing.

Extracted Key Phrases

5 Figures and Tables

Cite this paper

@inproceedings{Gwinnup2015TheAW, title={The AFRL-MITLL WMT15 System: There's More than One Way to Decode It!}, author={Jeremy Gwinnup and Tim Anderson and Grant Erdmann and Katherine Young and Christina May and Michaeel Kazi and Elizabeth Salesky and Brian Thompson}, booktitle={WMT@EMNLP}, year={2015} }