Phrase-based Parallel Fragments Extraction from Comparable Corpora

We present a phrase-based method to extract parallel fragments from the comparable corpora. We do this by introducing a force decoder based on the hierarchical phrase-based (HPB) translation model to detect the alignments in comparable sentence pairs. This method enables us to extract useful training data for statistical machine translation (SMT) system. We evaluate our method by fragment detection and large-scale translation tasks, which show that our method can effectively extract parallel fragments and improve the performance of the state-of-the-art SMT system.