This item is available under a Creative Commons License for non-commercial use only
1.2 COMPUTER AND INFORMATION SCIENCE
We evaluate a substitution based technique for improving Statistical Machine Translation performance on idiomatic multiword expressions. The method operates by performing substitution on the original idiom with its literal meaning before translation, with a second substitution step replacing literal meanings with idioms following translation. We detail our approach, outline our implementation and provide an evaluation of the method for the language pair English/Brazilian-Portuguese. Our results show improvements in translation accuracy on sentences containing either morphosyntactically constrained or unconstrained idioms. We discuss the consequences of our results and outline potential extensions to this process.
Salton, G., Ross, R. & Kelleher, J. (2014) Evaluation of a Substitution Method for Idiom Transformation in Statistical Machine Translation. 10th Workshop on Multiword Expres- sions (MWE 2014) at 14th Conference of the Euro- pean Chapter of the Association for Computational Linguistics,Gothenburg, Sweden, 26-30, April. doi:10.21427/D7BS4R