A Syntax-Driven Bracketing Model for Phrase-Based Translation

Syntactic analysis influences the way in which the source sentence is translated. Previous efforts add syntactic constraints to phrase-based translation by directly rewarding/punishing a hypothesis whenever it matches/violates source-side constituents. We present a new model that automatically learns syntactic constraints, including but not limited to constituent matching/violation, from training corpus. The model brackets a source phrase as to whether it satisfies the learnt syntactic constraints. The bracketed phrases are then translated as a whole unit by the decoder. Experimental results and analysis show that the new model outperforms other previous methods and achieves a substantial improvement over the baseline which is not syntactically informed.

• Type: Journal
• Year: 2009
• Where: ACL
• Authors: Deyi Xiong, Min Zhang, AiTi Aw, Haizhou Li
• Keywords: ACL 2009, Computational Linguistics, Learnt Syntactic Constraints, Phrase-based Translation, Syntactic Constraints