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...
Decoding algorithm is a crucial part in statistical machine translation. We describe a stack decoding algorithm in this paper. We present the hypothesis scoring method and the heu...
We achieved a state of the art performance in statistical machine translation by using a large number of features with an online large-margin training algorithm. The millions of p...
Taro Watanabe, Jun Suzuki, Hajime Tsukada, Hideki ...
Abstract. This paper describes an example-based machine translation (EBMT) method based on tree-string correspondence (TSC) and statistical generation. In this method, the translat...
Long distance word reordering is a major challenge in statistical machine translation research. Previous work has shown using source syntactic trees is an effective way to tackle ...