Otomatik çeviride regresyon modeli

Regression based machine translation (RegMT) approach provides a learning framework for machine translation, separating learning models for training, training instance selection, feature representation, and decoding. We use transductive learning framework for making RegMT computationally more scalable and consider model building step independently for each test sentence. We develop better training instance selection techniques than previous work from given parallel training sentences for achieving more accurate RegMT models using less training instances.We introduce L1 regularized regression as a better model than L2 regularized regression for statistical machine translation. Our results demonstrate that sparse regression models are better than L2 regularized regression for statistical machine translation in predicting target features, estimating word alignments, creating phrase tables, and generating translation outputs. We develop good evaluation techniques for measuring the performance of the RegMT model and the quality of the translations. F1 allows us to evaluate the performance of RegMT models without performing the decoding step, which can be computationally expensive.We use graph decoding on the prediction vectors represented in n-gram counts space or we decode using Moses after transforming the learned weight matrix representing the mappings between the source and target features to a phrase table that can be used by Moses during decoding. We demonstrate that sparse L1 regularized regression performs better than L2 regularized regression in German-English translation task and in Spanish-English translation task when using small sized training sets. Graph based decoding can provide an alternative to phrase-based decoding in translation domains having low vocabulary.