Evaluation of a Substitution Method for Idiom Transformation in Statistical Machine Translation
Giancarlo Dondoni Salton, Robert Ross, John D. Kelleher · 2014
We evaluate a substitution based technique for improving Statistical Machine Transla-tion performance on idiomatic multiword expressions. The method operates by per-forming substitution on the original idiom with its literal meaning before translation, with a second substitution step replac-ing literal meanings with idioms follow-ing translation. We detail our approach, outline our implementation and provide an evaluation of the method for the lan-guage pair English/Brazilian-Portuguese. Our results show improvements in trans-lation accuracy on sentences containing either morphosyntactically constrained or unconstrained idioms. We discuss the con-sequences of our results and outline poten-tial extensions to this process. 1