Paper: Kernel Regression Based Machine Translation

ACL ID N07-2047
Title Kernel Regression Based Machine Translation
Venue Human Language Technologies
Session Short Paper
Year 2007
Authors

We present a novel machine translation framework based on kernel regression techniques. In our model, the translation task is viewed as a string-to-string map- ping, for which a regression type learning is employed with both the source and the target sentences embedded into their ker- nel induced feature spaces. We report the experiments on a French-English transla- tion task showing encouraging results.