Feature-Rich Phrase-based Translation: Stanford University's Submission to the WMT 2013 Translation Task

2013 
We describe the Stanford University NLP Group submission to the 2013 Workshop on Statistical Machine Translation Shared Task. We demonstrate the eectiveness of a new adaptive, online tuning algorithm that scales to large feature and tuning sets. For both English-French and English-German, the algorithm produces feature-rich models that improve over a dense baseline and compare favorably to models tuned with established methods.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    26
    References
    7
    Citations
    NaN
    KQI
    []