The AFRL-MITLL WMT15 System: There’s More than One Way to Decode It!
By Jeremy Gwinnup, Tim Anderson, Grant Erdmann, Katherine Young, Christina May, Michaeel Kazi, Elizabeth Salesky, Brian Thompson. 2015
7 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Molecular Biology, Machine Translation
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jeremy Gwinnup
- Brian Thompson
- Katherine Young
- Tim Anderson
- Michaeel Kazi
- Elizabeth Salesky
- Grant Erdmann
- Felix Stahlberg
In Machine Translation
Citations in the corpus
- The AFRL-MITLL WMT16 News-Translation Task Systems (2016, methodology): “For submission system 2, we used the same approach as system 1, removing the class-factored language model and utilizing both the BigLM used in our WMT15 systems and a secondary language model built from data selected from the monolingual CommonCrawl corpus as outlined in §2.4.”