Accession Number:

AD1030409

Title:

The MITLL-AFRL IWSLT 2016 Systems

Descriptive Note:

Technical Report

Corporate Author:

MIT Lincoln Laboratory Lexington United States

Personal Author(s):

• Kazi,Michaeel
• Salesky,Elizabeth
• Thompson,Brian
• Taylor,Jonathon
• Gwinnup,Jeremy
• Anderson,Timothy
• Erdmann,Grant
• Hansen,Eric
• Ore,Brian
• Young,Katherine
• Hutt,Michael

Report Date:

2016-12-08

Pagination or Media Count:

8.0

Abstract:

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 approaches in machine translation and utilize system combination to create a composite system with the best characteristics of all MT approaches.

Descriptors:

• machine translation
• language translation
• automated speech recognition

Subject Categories:

• Linguistics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE