Bringing state-of-the-art machine translation to the user: personalized, on demand, and affordable

Andy Way — Applied Language Solutions, EAMT

Access to good quality Machine Translation (MT) has never been as easy as it is today. Portals such as Google Translate and Bing Translator facilitate huge amounts of translation requests on a daily basis, for an ever increasing spectrum of language pairs. People are finding many uses for the raw MT output provided by these, and other, freely available engines on the web, including gisting, assimilation, first drafts of translations for dissemination, etc. However, each of these systems is a 'one size fits all' solution, where no customization is available to the user. One alternative is to purchase a system, which may be overly expensive, or be sub-optimal for the type of documentation required to be translated. Another alternative is to install a freely available system such as Moses, but this may prove unduly onerous for the naïve user.

In this talk, we present SmartMATE, a portal which facilitates self-serve MT using state-of-the-art statistical MT (SMT). By means of a simple key-press, users can upload their own Translation Memory (TM) and glossaries, which are used to build an SMT system in very acceptable amounts of time. The SMT systems are thus, unlike in the above mentioned general-purpose portals, trained and tuned according to a users' need, and adhere to the required terminology. These systems can be exploited from SmartMATE's editing environment, which leverages MT with TM and the chosen glossaries, or via an API. According to user trials, this is a very exciting development, with the potential to vastly expand the user-base for self-serve SMT on a global basis.


Ultimo aggiornamento: 30/5/2016