Fast and Accurate Preordering for SMT using Neural Networks

Download: presentation.

Fast and Accurate Preordering for SMT using Neural Networks” by Adrià de Gispert, Gonzalo Iglesias, and William Byrne. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT 2015), June 2015.

Abstract

We propose the use of neural networks to model source-side preordering for faster and better statistical machine translation. The neural network trains a logistic regression model to predict whether two sibling nodes of the source-side parse tree should be swapped in order to obtain a more monotonic parallel corpus, based on samples extracted from the word-aligned parallel corpus. For multiple language pairs and domains, we show that this yields the best reordering performance against other state-of-the-art techniques, resulting in improved translation quality and very fast decoding.

Download: presentation.

BibTeX entry:

@inproceedings{nnpreohlt15,
   author = {Adri{\`a} de Gispert and Gonzalo Iglesias and William Byrne},
   title = {Fast and Accurate Preordering for SMT using Neural Networks},
   booktitle = {Proceedings of the Conference of the North American
	Chapter of the Association for Computational Linguistics - Human
	Language Technologies (NAACL HLT 2015)},
   month = jun,
   year = {2015},
   url = {http://www.aclweb.org/anthology/N/N15/N15-1105.pdf}
}

Back to Bill Byrne publications.