The Guardian published an interview with Tilde about building language technology services with multilingual open data. Headlined "Tilde is revolutionising language translation with open data," the interview appeared in the online edition of The Guardian on June 29.
In the interview, Tilde's team describes their ongoing work on MT: "Our custom machine translation (MT) is a powerful, indispensable tool for companies to boost translation productivity and instantly cross language barriers, fueled by the latest advances in AI, deep learning, and neural network technology."
The interview also details how Tilde leverages multilingual open data to build custom MT systems: "The raw material of language technology services such as MT is multilingual data. Resources - such as texts already translated in two or more languages – are used to develop language technology services by training complex algorithms to translate between languages."
As described in the interview, Tilde recently undertook a project to collect and process massive amounts of multilingual open data for EU languages. Called the TILDE MODEL corpus, the resources allow Tilde to develop even higher quality MT systems for multiple languages and domains.