Paper: Incremental Translation Utilizing Constituent Boundary Patterns

ACL ID C96-1070
Title Incremental Translation Utilizing Constituent Boundary Patterns
Venue International Conference on Computational Linguistics
Session Main Conference
Year 1996
Authors

We have proposed an incremental trans- lation method in Transfer-Driven Ma- chine Translation (TDMT). In this method, constituent boundary patterns are applied to an input in a bottom-up fashion. Also, by dealing with best-only substructures, the explosion of structural ambiguity is constrained and an efficient translation of a lengthy input can be achieved. Through preliminary exper- imentation our new TDMT has been shown to be more efficient while main- tMning translation quality.