papers AI Learner
The Github is limit! Click to go to the new site.

The Edit Distance Transducer in Action: The University of Cambridge English-German System at WMT16

2016-06-15
Felix Stahlberg, Eva Hasler, Bill Byrne

Abstract

This paper presents the University of Cambridge submission to WMT16. Motivated by the complementary nature of syntactical machine translation and neural machine translation (NMT), we exploit the synergies of Hiero and NMT in different combination schemes. Starting out with a simple neural lattice rescoring approach, we show that the Hiero lattices are often too narrow for NMT ensembles. Therefore, instead of a hard restriction of the NMT search space to the lattice, we propose to loosely couple NMT and Hiero by composition with a modified version of the edit distance transducer. The loose combination outperforms lattice rescoring, especially when using multiple NMT systems in an ensemble.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1606.04963

PDF

https://arxiv.org/pdf/1606.04963


Comments

Content