The PangeaMT Platform: User-Empowering and Data-Driven, In-Domain Machine Translation
Manuel Herranz & Elia Yuste
Thursday, 26 September, 2013
Elia Yuste and Manuel Herranz of Pangeanic provide an overview of the most important and innovative features of the PangeaMT Platform. Learn about how to be in control of your domain-specific data assets and MT engines at all times. PangeaMT was born out of the translation automation needs of Pangeanic (PAN, http://www.pangeanic.com), a forward-looking LSP, in late 2009. Since then, the PangeaMT team has served a significant number of corporations and other language service providers worldwide that also believed in user-centric and data-geared, in-domain MT customizations. Focused on open standards, PangeaMT has evolved from being the first commercial application of Moses, adding workflow and management systems, to offering an adaptive and easy-to-use MT platform, with in-domain data management and engine training capabilities. While first-time customization and training data consultancy, including clean-up and reporting, impregnates each and every PangeaMT development, it is definitely worth learning more about what the PangeaMT platform can do for you once your first-time engine(s) are made available to the user. This webinar will show you the MT features and deployment scenarios that go far beyond the actual act of requesting machine-translated output in a limited fashion. Learn about how to be in control of your domain-specific data assets and MT engines at all times!
Active in the European language industry since the 1990s, Manuel Herranz is MD and founder of Pangeanic B.I Europa, a leading Spanish translation company with strong historical and commercial links with the partner offices in Japan and China. A firm believer in language automation, Manuel directed ISO qualification and RBMT implementation for patent work.
Elia Yuste has been instrumental in the scientific and commercial advancement of PangeaMT as a user-empowering MT solution range. In previous professional lives, she worked for Google Ireland, several European translation tech companies and universities. She also launched and managed a language service at the Spanish-Swiss Chamber of Commerce in Zurich and has been involved with translation since she was 22. - See more at: https://www.gala-global.org/ondemand/pangeamt-platform-user-empowering-and-data-driven-domain-machine-translation#sthash.ys3mH143.dpuf
Most machine translation output is fine for basic Western LSP needs, as they usually translate within European...
Machine translation is great when it works, but it fails often and in unpredictable ways. What causes bad machine...