CUED Publications database

Fast and accurate preordering for SMT using neural networks

De Gispert, A and Iglesias, G and Byrne, B (2015) Fast and accurate preordering for SMT using neural networks. In: UNSPECIFIED pp. 1012-1017..

Full text not available from this repository.

Abstract

© 2015 Association for Computational Linguistics. 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.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:04
Last Modified: 03 Aug 2017 03:21
DOI: