57 search results - page 5 / 12 » A Smorgasbord of Features for Statistical Machine Translatio... |
MT
2007
13 years 6 months ago
2007
This paper describes the framework of the StatCan Daily Translation Extraction System (SDTES), a computer system that maps and compares webbased translation texts of Statistics Can...
ACL
2007
13 years 8 months ago
2007
Data sparseness is one of the factors that degrade statistical machine translation (SMT). Existing work has shown that using morphosyntactic information is an effective solution t...
COLING
2008
13 years 8 months ago
2008
Och's (2003) minimum error rate training (MERT) procedure is the most commonly used method for training feature weights in statistical machine translation (SMT) models. The u...
ACL
2008
13 years 8 months ago
2008
Phrase-based decoding produces state-of-theart translations with no regard for syntax. We add syntax to this process with a cohesion constraint based on a dependency tree for the ...
MT
2002
13 years 6 months ago
2002
We present MARS (Multilingual Automatic tRanslation System), a research prototype speech-to-speech translation system. MARS is aimed at two-way conversational spoken language trans...