Improved Reordering for Phrase-Based Translation using Sparse Features

Colin Cherry

There have been many recent investigations into methods to tune SMT systems using large numbers of sparse features. However, there have not been nearly so many examples of helpful sparse features, especially for phrase-based systems. We use sparse features to address reordering, which is often considered a weak point of phrase-based translation. Using a hierarchical reordering model as our baseline, we show that simple features coupling phrase orientation to frequent words or word-clusters can improve translation quality, with boosts of up to 1.2 BLEU points in Chinese-English and 1.8 in Arabic-English. We compare this solution to a more traditional maximum entropy approach, where a probability model with similar features is trained on word-aligned bitext. We show that sparse decoder features outperform maximum entropy handily, indicating that there are major advantages to optimizing reordering features directly for BLEU with the decoder in the loop.

Back to Papers Accepted