Thanks for your interest in DoMY. It's been almost 2 months since the media first mentioned DoMY. We have almost 100 registered users on the web site, but feedback has been sparse. The feedback we have received has been positive and we are updating DoMY based on user requests. The biggest user criticism has been we need better documentation. It's in the works!
DoMY CE gives users 100% Moses. So, it's not a question of Moses vs. DoMY. DoMY includes all of Moses and its data preparation and training/tuning scripts. DoMY installs, compiles and updates the Operating System to find Moses tools. We also add our tool chain called CorpusFiltergraph that provides a variety of packaged data preparation and translation workflows.
For example, the Moses "clean-corpus-n.perl" script deletes pairs of parallel corpora that don't match the sentences length or ratio. The DoMY equivalent is the "aligner-clean-corpus-n" plug-in which filters the same data, but sends the mis-matched parallel phrases to a different output instead of discarding them. Users can then review the data, and re-insert it as parallel corpora or language model data.
We're preparing to launch the Pro version. The first release includes some minor functionality improvements and enhanced techniques to remove inappropriate training data.
Thank you again for inviting user feedback. We, too look forward to their comments.
Save time by automatically extracting terms. 15% off!
SDL MultiTerm Extract 2011 allows you to automatically create candidate term lists from your existing documentation. This removes the manual effort involved with traditional terminology creation, allowing you to rapidly add terms to SDL MultiTerm.
A fully featured online CAT tool and TMS, with no installation required, and a simple, intuitive interface. Maximize linguistic assets by sharing in real time as you collaborate with colleagues. Make use of next generation, cloud-based translation technol