Exploiting source similarity for SMT using context-informed features
Stroppa, Nicolas, van den Bosch, Antal and Way, AndyORCID: 0000-0001-5736-5930
(2007)
Exploiting source similarity for SMT using context-informed features.
In: TMI-07 - Proceedings of The 11th Conference on Theoretical and Methodological Issues in Machine Translation, 7-9 September 2007, Skövde, Sweden.
In this paper, we introduce context informed features in a log-linear phrase-based SMT framework; these features enable us to exploit source similarity in addition to target similarity modeled by the language model. We
present a memory-based classification framework that enables the estimation of these features while avoiding
sparseness problems. We evaluate the performance of our approach on Italian-to-English and Chinese-to-English translation tasks using a state-of-the-art phrase-based SMT
system, and report significant improvements for both BLEU and NIST scores when adding the context-informed features.