Statistically motivated example-based machine translation using translation memory
Dandapat, Sandipan, Morrissey, Sara, Kumar Naskar, Sudip and Somers, Harold
(2010)
Statistically motivated example-based machine translation using translation memory.
In: the 8th International Conference on Natural Language Processing ICON 2010, 8 - 11 Dec. 2010, Kharagpur, India.
In this paper we present a novel way of integrating Translation Memory into an Example-based Machine translation System (EBMT) to deal with the issue of low
resources. We have used a dialogue of 380 sentences as the example-base for our system. The translation units in the
Translation Memories are automatically extracted based on the aligned phrases (words) of a statistical machine translation (SMT) system. We attempt to use the approach to improve translation from English to Bangla as many statistical machine translation systems have difficulty
with such small amounts of training data. We have found the approach shows improvement over a baseline SMT system.