Google recently released the Google Translator Toolkit. The Translator Toolkit allows users to easily upload text, has Google Translate’s existing functionality to automatically translate the text, and then adds “Translation Memories” which is a database of prior human translations.
A translation memory (TM) is a database of human translations. As you translate new sentences, we automatically search all available translation memories for previous translations similar to your new sentence. If such sentences exist, we rank and then show them to you. Comparing your translation to previous human translations improves consistency and saves you time: you can reuse previous translations or adjust them to create new, more contextually appropriate translations. When you finish translating documents in Google Translator Toolkit, we save your translations to a translation memory so you or other translators can avoid duplicating work.
Translation Memories is an excellent example of a smart technological idea because its service is embedded within a use case that could sustainably and equitably support all involved. Users are provided with an easy tool to do translations, and a tool that will continue to improve as they use it. Google gains access to translations and translations in context. This is the type of data that can easily be used (or much more easily than most) to better train computer translations, which can in turn improve Google’s translations overall and Google’s search engine results in other languages.
The Google Translator Toolkit has a limited set of languages right now, but it should improve as more texts in more languages are available overall and as the Google Translator Toolkit improves. The Google Translator Toolkit is a smart example of aiding small, current needs–current needs for an easy, online, collaborative tool for translations–to aid larger concerns like the need for better translations overall which requires human translations to improve automatic translations and which will be an ongoing process.
My current interest is in hoping that the Google Translator Toolkit soon adds Papiemento and Papiementu because the Digital Library of the Caribbean (dLOC) already includes texts in Papiemento and Papiementu. As dLOC adds more partners and more languages, more translations will be needed and more tools–especially those that ease collaborative work and shared results–are always welcome.