Home » Portfolio » Mini-Portfolio for Advanced CAT Tools

About Me

I have a passion for interactive entertainment and technology, and am interested in creating and curating content for the modern world.

Exceptional language, writing, proofing, editing and speaking ability; eager to learn and apply new and varied skills. Extroverted and unafraid to create new connections, and has a proven ability to maintain and nurture professional networks.

Mini-Portfolio for Advanced CAT Tools

This semester at MIIS, a lot of focus was put on learning how to use different Computer Assisted Translation tools and Translation Management Systems, as well as developing skills to learn any programs we might meet in our work.

Our most ambitious project by far was training a SMT Engine using the Microsoft Translator Hub. Our group decided to create an engine that would be able to machine translate Playstation system instruction manuals. To look at our project in detail, you can check out our statement of work and our presentation on lessons learned here, but it will suffice to say that the scale of the project greatly exceeded our initial expectations. We had to use PDF versions of various Playstation manuals to align, and the English versions differed from the Japanese versions at many points. Hours were spent on just alignment.

But eventually we ended up with a decent engine! With a larger library of correctly aligned files and use of human post-editing, our group decided that an engine for Playstation manuals could be feasible with the proper up-stream preparation.

We also experimented a bit individually with ModernMT, and open-source translation engine option. This was a pretty interesting experiment that required installing Linux and a lot of troubleshooting for things I had never encountered before.

All things considered, I was pretty pleased with the results! By the end of it, I had a working engine, and the Linux command line did make me feel rather hacker-y.

Lastly, we each made an instructional video for any tool we choose that could help in a localization workflow. I chose to do mine on the “Automatic Domain Terminology Extraction System ‘Gensen Web'” developed by the University of Tokyo Library System — a tool for extracting terminology from Japanese documents, including PDF. It’s a pretty simple tool, but if you want a head start on working it, please check out my instructional video found here.

I hope that the different guides that I’ve posted this year have helped you out! I don’t plan on posting much over the summer, but if something comes up, I may. Looking forward to learning and sharing more in fall!

Sites DOT MIISThe Middlebury Institute site network.