As part of Pangeanic’s machine translation division, collaborates with machine translation EU program Casmacat, a next-generation workbench being developed by leading machine translation and pattern-recognition authorities such as University of Edinburgh’s Prof. Philipp Koehn, Valencia’s Polytechnic’s Prof. Francisco Casacuberta and Copenhagen Business School Prof. Michael Carl.
“I’m very excited to align Pangeanic’s experienc with the cream of EU research for the next generation of machine translation tools and workbenches. Casmacat is an example of machine translation as a productivity enhancer”, said Alex Helle, Pangeanic’s Head of Machine Translation Research. “Furthermore, initial research shows that it is possible to integrate the best of statistical reporting and confidence scores, plus translator’s aids into a single, useful workbench.” Mr Helle continued.
Pangeanic will add testing expertise in languages, with little or no affinity to English like Japanese and Chinese into, also testing Spanish. Particular attention will also be paid to morphologically-rich languages like German, as well as compatibility with real-life translation scenarios, where companies have to translate format-rich content which includes many types of tags and different xml flavors. “We have already started experimenting with the first sets of data in Japanese. We look forward to check the tests and work on further experimentation with the project’s algorithms so that the top of European research will enhance our own machine translation service product lines at PangeaMT and provide more efficient and user-friendly post-editing methods”.
While the benefits of machine translation to speed publication and translation processes are no longer argued, post-editing and the acceptance of the technology by translators as a productivity tool is often a difficult hurdle for translation companies and translation departments. CASMACAT aims at providing interactive methods to engage translators by using several post-editing techniques, from confidence score color identification to suggestions. Pangeanic’s role is to test the latest in research in real translation processes in provide feedback to researchers and customize a version of the machine translation workbench.
Casmacat’s User’s Group homepage: http://www.casmacat.eu/index.php?n=Main.UserGroup