The objective of the work package 3 “Database and MT Infrastructure” is to carry out the porting of existing technologies and algorithms through a big data approach. It also includes aspects of research and innovation in order to achieve machine translation training in real time and to improve translation quality through the exploitation of context information.
This report is the first deliverable of WP3. It describes the current status of the implementation of the technologies and algorithms the consortium has worked on in the first year of the project.
In particular, Section 3 describes the overall MMT architecture by quickly introducing each single component and its interactions in the training and testing phases. Section 4 focuses on the context analyser, which informs the adaptation process of machine translation by finding the closest domains to the input document. Section 5 describes the machine translation engine, which includes text pre- and post-processing modules, the word aligner, adaptive translation and language models, and the MT engine. Section 6 outlines preliminary development carried out to distribute the MMT architecture over a computer network.
Finally, Section 7 presents the testing infrastructure developed to track progress of MMT in terms of MT performance.