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 describe an open-source toolkit for statistical machine translation whose novel contributions are (a) support for linguistically motivated factors, (b) confusion network decodi...
Philipp Koehn, Hieu Hoang, Alexandra Birch, Chris ...
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...