PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A Deep Learning Approach to Machine Transliteration
Thomas Deselaers, Sasa Hasan, Oliver Bender and Hermann Ney
In: EACL 2009 Workshop on Statistical Machine Translation, 31 Mar 2009, Athens, Greece.


In this paper we present a novel transliteration technique which is based on deep belief networks. Common approaches use finite state machines or other methods similar to conventional machine translation. Instead of using conventional NLP techniques, the approach presented here builds on deep belief networks, a technique which was shown to work well for other machine learning problems. We show that deep belief networks have certain properties which are very interesting for transliteration and possibly also for translation and that a combination with conventional techniques leads to an improvement over both components on an Arabic-English transliteration task.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Natural Language Processing
ID Code:5734
Deposited By:Thomas Deselaers
Deposited On:08 March 2010