Online Large-Margin Training for Statistical Machine Translation

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 parameters were tuned only on a small development set consisting of less than 1K sentences. Experiments on Arabic-toEnglish translation indicated that a model trained with sparse binary features outperformed a conventional SMT system with a small number of features.

• Type: Conference
• Year: 2007
• Where: EMNLP
• Authors: Taro Watanabe, Jun Suzuki, Hajime Tsukada, Hideki Isozaki
• Keywords: EMNLP 2007, Large-margin Training Algorithm, Natural Language Processing, Sparse Binary Features, Statistical Machine Translation