Let's MT!

Machine Translation for Everybody

Platform for Online Sharing of Training Data and Building User Tailored MT

In recent years SMT has provided a major breakthrough in MT development providing a cost effective and fast way to build MT systems. Current systems are built on the data accessible on the web, but it is just a fraction of all parallel texts. Majority of valuable parallel texts still reside in the local systems of different corporations, public and private institutions, desktops of individual users.

LetsMT! will be a collaborative platform that thrives on resources contributed by its users. It will have a major breakthrough regarding the availability of parallel language resources and, consequently, machine translation services of good and acceptable quality for less-covered languages where the current machine translation systems perform poorly due to limited availability of training data.

LetsMT! will provide a platform where:
  • Users will contribute with user-provided content by uploading their parallel texts
  • Directory of web and offline resources gathered by LetsMT! as well as user provided links to other sources not yet included in LetsMT! repository
  • Automated training of SMT systems from specified collections of training data
  • Larger donors or paying customers will be able to specify particular training data collections and build MT engines from these collections
  • Paying customers will be able to use LetsMT platform for tailoring MT system to their needs from their non-public data
  • Users will be involved in MT evaluation
The project will extend the use of existing state-of-the-art SMT methods that will be applied to data supplied by users to produce better-trained machine translation solutions. LetsMT! will integrate Moses, the freeware statistical machine translation engine, and Giza++, the open-source corpus alignment tool, providing simple and easy-to-use human interfaces for this software. The solution will deliver the following core functionality:
  • website for upload of parallel corpora and building of specific MT solutions
  • website for translation where source text can be typed and translated
  • translation widget provided for free inclusion into websites to translate their content
  • browser plug-ins or add-ons that would allow the quickest access to translation
  • web service for integration in CAT tools and other applications

LetsMT! Partners

This project is a joint effort of a well balanced consortium of four leading European R&D centres and three industrial companies. The partners comprise expertise in statistical machine translation, natural language processing, corpus linguistics, web solutions, large information systems, and software engineering.

The project is in negotiations for support from EU Competitiveness and Innovation framework Programme - ICT PSP