The MIT-LL/AFRL IWSLT-2013 MT system

Michaeel Kazi, Michael Coury, Elizabeth Salesky, Jessica Ray, Wade Shen, Terry Gleason, Tim Anderson, Grant Erdmann, Lane Schwartz, Brian Ore, Raymond Slyh, Jeremy Gwinnup, Katherine Young, Michael Hutt


Abstract
This paper describes the MIT-LL/AFRL statistical MT system and the improvements that were developed during the IWSLT 2013 evaluation campaign [1]. 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, Chinese to English, Arabic to English, and English to French TED-talk translation task. We also applied our existing ASR system to the TED-talk lecture ASR task. We discuss the architecture of the MIT-LL/AFRL MT system, improvements over our 2012 system, and experiments we ran during the IWSLT-2013 evaluation. Specifically, we focus on 1) cross-entropy filtering of MT training data, and 2) improved optimization techniques, 3) language modeling, and 4) approximation of out-of-vocabulary words.
Anthology ID:
2013.iwslt-evaluation.17
Volume:
Proceedings of the 10th International Workshop on Spoken Language Translation: Evaluation Campaign
Month:
December 5-6
Year:
2013
Address:
Heidelberg, Germany
Editor:
Joy Ying Zhang
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
Language:
URL:
https://aclanthology.org/2013.iwslt-evaluation.17
DOI:
Bibkey:
Cite (ACL):
Michaeel Kazi, Michael Coury, Elizabeth Salesky, Jessica Ray, Wade Shen, Terry Gleason, Tim Anderson, Grant Erdmann, Lane Schwartz, Brian Ore, Raymond Slyh, Jeremy Gwinnup, Katherine Young, and Michael Hutt. 2013. The MIT-LL/AFRL IWSLT-2013 MT system. In Proceedings of the 10th International Workshop on Spoken Language Translation: Evaluation Campaign, Heidelberg, Germany.
Cite (Informal):
The MIT-LL/AFRL IWSLT-2013 MT system (Kazi et al., IWSLT 2013)
Copy Citation:
PDF:
https://aclanthology.org/2013.iwslt-evaluation.17.pdf