The MITLL-AFRL IWSLT 2014 MT system

Michaeel Kazi, Elizabeth Salesky, Brian Thompson, Jessica Ray, Michael Coury, Tim Anderson, Grant Erdmann, Jeremy Gwinnup, Katherine Young, Brian Ore, Michael Hutt


Abstract
This report summarizes the MITLL-AFRL MT and ASR systems and the experiments run using them during the 2014 IWSLT evaluation campaign. Our MT system is much improved over last year, owing to integration of techniques such as PRO and DREM optimization, factored language models, neural network joint model rescoring, multiple phrase tables, and development set creation. We focused our eforts this year on the tasks of translating from Arabic, Russian, Chinese, and Farsi into English, as well as translating from English to French. ASR performance also improved, partly due to increased eforts with deep neural networks for hybrid and tandem systems. Work focused on both the English and Italian ASR tasks.
Anthology ID:
2014.iwslt-evaluation.8
Volume:
Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign
Month:
December 4-5
Year:
2014
Address:
Lake Tahoe, California
Editors:
Marcello Federico, Sebastian Stüker, François Yvon
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
65–72
Language:
URL:
https://aclanthology.org/2014.iwslt-evaluation.8
DOI:
Bibkey:
Cite (ACL):
Michaeel Kazi, Elizabeth Salesky, Brian Thompson, Jessica Ray, Michael Coury, Tim Anderson, Grant Erdmann, Jeremy Gwinnup, Katherine Young, Brian Ore, and Michael Hutt. 2014. The MITLL-AFRL IWSLT 2014 MT system. In Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 65–72, Lake Tahoe, California.
Cite (Informal):
The MITLL-AFRL IWSLT 2014 MT system (Kazi et al., IWSLT 2014)
Copy Citation:
PDF:
https://aclanthology.org/2014.iwslt-evaluation.8.pdf