In a major step to improve access to patent documents in multiple languages the European Patent Office today launched a new machine translation service, called patent translate, on the EPO’s website. The service uses Google’s Translate technology and enables translation from and to English for French, German, Spanish, Italian, Portuguese and Swedish, covering approximately 90% of all patents issued in Europe. By the end of 2014, the service will also be able to translate patents from and into all 28 languages of the EPO member states, as well as Chinese, Japanese, Korean and Russian.
“The launch today is a landmark towards the removal of language barriers worldwide from patent documentation”, EPO President Benoît Battistelli stated. “Patent translate enables businesses and innovators to identify relevant patent documents and to translate them in their own language. It also facilitates the implementation of the unitary patent which includes an important chapter on translation. The new tool underlines the leading role of the EPO as largest provider of free patent data, and efficiently supports the objective of both partners, Google and the EPO, of improving the accessibility of technical information contained in patents irrespective of the language of the user.”
“The partnership between the EPO and Google is a great technical solution to the complex challenge of delivering better translations of – and better multilingual access to – patent information,” said Antoine Aubert, head of public policy, Google Brussels. “We’re delighted to be offering the service in seven languages via the EPO’s website and the Google Translate service, and we’ll be working to further optimise our system – and make the other 21 EPO languages available in the coming years.”
The cooperation with Google launched less than one year ago has already led to a significant improvement in the quality of the machine translation of patents. This was achieved by the introduction of several hundred thousand high quality translations of patents in the seven languages provided by the EPO, which Google used to ‘train’ its Google translate system. Further gains will be achieved as more language corpora are added over time.
A next batch including Danish, Dutch, Finnish, Greek, Hungarian and Norwegian will be uploaded in 2013, and by the end of 2014 the project should be completed for the 32 languages.