Paper: Bridging Morpho-Syntactic Gap between Source and Target Sentences for English-Korean Statistical Machine Translation

ACL ID P09-2059
Title Bridging Morpho-Syntactic Gap between Source and Target Sentences for English-Korean Statistical Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2009
Authors

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.