Bridging morpho-syntactic gap between source and target sentences for EnglishKorean statistical machine translation

Often, Statistical Machine Translation (SMT) between English and Korean suf-fers from null alignment. Previous studies have attempted to resolve this problem by removing unnecessary function words, or by reordering source sentences. However, the removal of function words can cause a serious loss in information. In this pa-per, we present a possible method of bridg-ing the morpho-syntactic gap for English-Korean SMT. In particular, the proposed method tries to transform a source sen-tence by inserting pseudo words, and by reordering the sentence in such a way that both sentences have a similar length and word order. The proposed method achieves 2.4 increase in BLEU score over baseline phrase-based system.