European Commission logo
English English
CORDIS - EU research results
CORDIS

Article Category

News
Content archived on 2023-03-02

Article available in the following languages:

European project to develop automatic learning and translation system for EU languages

With the exploding demand for translations since enlargement, a new European project is developing a computer automatic translation system for the 23 official languages now spoken in the European Union. The €2.5 million Euromatrix project is aiming to achieve a technolo...

With the exploding demand for translations since enlargement, a new European project is developing a computer automatic translation system for the 23 official languages now spoken in the European Union. The €2.5 million Euromatrix project is aiming to achieve a technological breakthrough in the field of computer automatic translation through the development of statistical translation techniques. Instead of using complex handmade systems of rules requiring decades of concentrated work to build and refine, the team behind the project will use the body of pre-translated work for the application of automatic learning processes. The result will be a new computer program which has taught itself to translate. According to Professor Hans Uszkoreit, the leader of the project from Saarland University, Germany, 'The human translator must have perfect command of the target language because it is more difficult to compose stylistically excellent language than it is to simply understand content. The statistical translation programs can be similarly perfected in the language into which they translate.' 'This is done via automatic learning, for which large supplies of monolingual text, found in abundance in the internet, are necessary. These autodidacts of translation systems are still far from perfect, but they are improving year by year. An investigation of existing technology shows that both statistical and rule-based translation methods may still make many mistakes - but they do not make the same mistakes!' The project will also organise a competition aimed at other European researchers and companies to find the best translation system.