MyMemory: next generation Translation Memory technology

MyMemory is the world's largest Translation Memory: 100m segments by end 2008

Just like a traditional TM, MyMemory stores segments and their translations, supporting translators with matches and concordance. It differs from traditional technologies in terms of the project's ambitious scale, and its centralized, collaborative architecture. Anyone may consult or contribute to MyMemory via the internet, although contributions are carefully vetted for quality.

Custom memories in an instant for translators, LSPs and customers

MyMemory supports on-the-fly creation of customized memories for specific jobs: just upload the files and download a made-to-measure memory that may be opened with any CAT tool. Users can also upload memories to back them up, or to consolidate multiple memories into a single, searchable reference resource. These features are even available without publicly sharing uploaded memories, although this practice is encouraged wherever legally possible.

Crawling the multilingual web for more translation segments

The web contains a mass of unstructured multilingual content: MyMemory is systematically searching and downloading millions of translated pages in order to extract new memory segments. These 'web segments' are classified by source, subject and quality to facilitate subsequent searches.

So what's next?

MyMemory's objective is to help translators work faster and better by rendering existing translations universally searchable and accessible. The next big thing is going to be seamless integration with CAT tools, which will see MyMemory move right onto your desktop as a virtual local memory.

If you have feedback or suggestions on how to improve MyMemory, please write to us.