Paper: Using unlabeled dependency parsing for pre-reordering for Chinese-to-Japanese statistical machine translation

ACL ID W13-2806
Title Using unlabeled dependency parsing for pre-reordering for Chinese-to-Japanese statistical machine translation
Venue Workshop on Hybrid Approaches to Translation
Session
Year 2013
Authors

Chinese and Japanese have a different sen- tence structure. Reordering methods are effective, but need reliable parsers to ex- tract the syntactic structure of the source sentences. However, Chinese has a loose word order, and Chinese parsers that ex- tract the phrase structure do not perform well. We propose a framework where only POS tags and unlabeled dependency parse trees are necessary, and linguistic knowl- edge on structural difference can be en- coded in the form of reordering rules. We show significant improvements in transla- tion quality of sentences from news do- main, when compared to state-of-the-art reordering methods.