KantanMT Releases New Preprocessing Feature to Improve Machine Translation Quality
KantanMT released a new client file preprocessing feature, which improves the quality of machine translated files. The KantanMT Community can prepare their files for translation by creating, testing and managing customised rules to improve the quality of MT output.
The KantanMT Community can use the feature to ‘normalise’ or prepare their files for translation by creating, testing and managing customised rules that result in higher quality machine translation output.
The feature uses a series of search and replace rules, based on GENTRY file parser technology to normalise the file for translation before the Machine Translation decoding process.
Benefits of using KantanMT’s translation preprocessing feature:
Improved Translation Quality: Machine Translated files will be of a higher quality and will require less post-editing
Faster time to Market: The translation review process will be shortened improving time to market for translation
Increased Productivity: Reduced post-editing ensures faster translation turnaround increasing translation productivity
To utilise the preprocessing feature users create GENTRY rule files, which can be uploaded alongside files for translation or ‘client files’ in the profiles dashboard. Rules can be created in the PEX (Post-Editing Automation) rule editor. The editor displays the effect of rules on both the source and target components of the rejected segment in real-time, and via a user interface, similar to the Microsoft Word track changes feature.
“Increasing productivity and translation efficiency are key drivers for success in the translation supply chain,” said Tony O’Dowd, Founder and Chief Architect of KantanMT. “Building on the KantanPreprocessor™for training data we introduced a few months ago, our clients can now normalise their files for translation, which will further improve quality and translation efficiency.”
For more information, or to start using the platform, send an email to email@example.com.
KantanMT.com is a leading SaaS based machine translation platform that enables users to develop and manage customised machine translation engines in the cloud. The innovative technologies offered on the KantanMT.com platform enable users to easily build MT engines in over 750 language combinations, seamlessly integrating into localization workflows and web applications. KantanMT is based in the INVENT Building, DCU Campus, Dublin 9.