A platform for research: civil engineering, architecture and urbanism
MIT-LL/AFRL MT System
The MIT-LL/AFRL MT system is a statistical phrase-based translation system that implements many modern SMT training and decoding techniques. Our system was designed with the long term goal of dealing with corrupted ASR input for Speech-to-Speech MT applications. This paper will discuss the architecture of the MIT-LL/AFRL MT system, and experiments with manual and ASR transcription data that were run as part of the IWSLT-2005 Chinese-to-English evaluation campaign.
MIT-LL/AFRL MT System
The MIT-LL/AFRL MT system is a statistical phrase-based translation system that implements many modern SMT training and decoding techniques. Our system was designed with the long term goal of dealing with corrupted ASR input for Speech-to-Speech MT applications. This paper will discuss the architecture of the MIT-LL/AFRL MT system, and experiments with manual and ASR transcription data that were run as part of the IWSLT-2005 Chinese-to-English evaluation campaign.
MIT-LL/AFRL MT System
W. Shen (author) / B. Delaney (author) / T. Anderson (author)
2005
6 pages
Report
No indication
English
British Library Online Contents | 2006
|AFRL-MITLL WMT16 News-Translation Task Systems
NTIS | 2016
|Overview of the DARPA/AFRL/NASA Smart Wing program
British Library Conference Proceedings | 1999
|British Library Conference Proceedings | 1999
|