The AFRL-MITLL WMT15 System: There's More than One Way to Decode It!
Abstract
This paper describes the AFRL-MITLL statistical MT system 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 phrase-based 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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 25, 2015
- Accession Number
- AD1034899
Entities
People
- Brian J. Thompson
- Christina May
- Elizabeth E. Salesky
- Grant Erdmann
- Jeremy Gwinnup
- Katherine Young
- Michaeel M. Kazi
- Timothy Anderson
Organizations
- MIT Lincoln Laboratory