The Regression Model of Machine Translation : Learning, Instance Selection, Decoding, and Evaluation

Mehmet Ergun Biçici

ISBN 10: 3846507490 / ISBN 13: 9783846507490

Editore: LAP LAMBERT Academic Publishing, 2011

Riguardo questo articolo

nach der Bestellung gedruckt Neuware - Printed after ordering - Regression based machine translation (RegMT) model provides a learning framework for machine translation, separating learning models for training, training instance selection, feature representation, and decoding. Transductive learning approach employs training instance selection algorithms that not only make RegMT computationally more scalable but also improve the performance of standard statistical machine translation (SMT) systems. Sparse regression models for SMT are introduced and the obtained results demonstrate that sparse regression models perform better than other learning models 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. We demonstrate that sparse L1 regularized regression performs better than L2 regularized regression in the German-English translation task and in the 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. Codice articolo 9783846507490

Dati bibliografici

Titolo: The Regression Model of Machine Translation ...

Casa editrice: LAP LAMBERT Academic Publishing

Data di pubblicazione: 2011

Legatura: Taschenbuch

Condizione: Neu

Descrizione articolo

Riassunto:

Regression based machine translation (RegMT) model provides a learning framework for machine translation, separating learning models for training, training instance selection, feature representation, and decoding. Transductive learning approach employs training instance selection algorithms that not only make RegMT computationally more scalable but also improve the performance of standard statistical machine translation (SMT) systems. Sparse regression models for SMT are introduced and the obtained results demonstrate that sparse regression models perform better than other learning models 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. We demonstrate that sparse L1 regularized regression performs better than L2 regularized regression in the German-English translation task and in the 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.

L'autore:

Mehmet Ergun Biçici received his Bachelor of Science degree in Computer Science from Bilkent University, Ankara, Turkey in 2000. He obtained Master of Science degree in Computer Science from North Carolina State University, USA, in 2002. He obtained the Doctor of Philosophy degree in Computer Engineering at Koç University, Istanbul, Turkey in 2011.