Paper: Experiments with POS-based restructuring and alignment-based reordering for statistical machine translation

ACL ID W13-2812
Title Experiments with POS-based restructuring and alignment-based reordering for statistical machine translation
Venue Workshop on Hybrid Approaches to Translation
Session
Year 2013
Authors

This paper presents the methods which are based on the part-of-speech (POS) and auto alignment information to improve the quality of machine translation result and the word alignment. We utilize different types of POS tag to restructure source sentences and use an alignment-based reordering method to im- prove the alignment. After applying the reor- dering method, we use two phrase tables in the decoding part to keep the translation perfor- mance. Our experiments on Korean-Chinese show that our methods can improve the align- ment and translation results. Since the pro- posed approach reduces the size of the phrase table, multi-tables are considered. The combi- nation of all these methods together would get the best translation result.