The AFRL-MITLL WMT16 News-Translation Task System: We put NMT in your MT Rescoring so you can MT while you MT
نویسندگان
چکیده
This paper describes the AFRL-MITLL statistical machine translation systems and the improvements that were developed during the WMT16 evaluation campaign. As part of these efforts we’ve adapted a variety new techniques to our previous years’ systems including Neural Machine Translation, additional out-of-vocabulary transliteration techniques, and morphology generation. Preliminary results are denoted with *.
منابع مشابه
The AFRL-MITLL WMT16 News-Translation Task Systems
This paper describes the AFRL-MITLL statistical machine translation systems and the improvements that were developed during the WMT16 evaluation campaign. As part of these efforts we have adapted a variety new techniques to our previous years’ systems including Neural Machine Translation, additional out-of-vocabulary transliteration techniques, and morphology generation.
متن کاملThe MIT-LL/AFRL IWSLT-2007 MT system
The MIT-LL/AFRL MT system implements a standard phrase-based, statistical translation model. It incorporates a number of extensions that improve performance for speechbased translation. During this evaluation our efforts focused on the rapid porting of our SMT system to a new language (Arabic) and novel approaches to translation from speech input. This paper discusses the architecture of the MI...
متن کاملThe MITLL - AFRL IWSLT 2016 Systems †
This report summarizes the MITLL-AFRL MT and ASR systems and the experiments run during the 2016 IWSLT evaluation campaign. Building on lessons learned from previous years’ results, we refine our ASR systems and examine the explosion of neural machine translation systems and techniques developed in the past year. We experiment with a variety of phrase-based, hierarchical and neural-network appr...
متن کاملThe MITLL - AFRL IWSLT 2016
This report summarizes the MITLL-AFRL MT and ASR systems and the experiments run during the 2016 IWSLT evaluation campaign. Building on lessons learned from previous years’ results, we refine our ASR systems and examine the explosion of neural machine translation systems and techniques developed in the past year. We experiment with a variety of phrase-based, hierarchical and neural-network appr...
متن کاملThe AFRL-MITLL WMT15 System: There's More than One Way to Decode It!
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 ...
متن کامل