Stacking for Statistical Machine Translation
Majid Razmara and Anoop Sarkar
The 51st Annual Meeting of the Association for Computational Linguistics - Short Papers (ACL Short Papers 2013)
Sofia, Bulgaria, August 4-9, 2013
We propose the use of stacking, an ensemble learning technique, to the training and tuning of statistical machine translation (SMT) models. A diverse ensemble of weak learners is created using the same SMT engine by manipulating the training data and a strong model is created by combining the weak models on-the-fly. Experimental results on two language pairs and three different sizes of training data show significant improvements of up to 4 BLEU points over a conventionally trained SMT model.
Conference Manager (V2.61.0 - Rev. 2792M)