News

Language I/O to Highlight Innovative Tech at Top Industry Conference

February 28, 2020

GCC-2020 (5).jpgMarch 9-11, Language I/O will highlight its proprietary machine translation acceleration technology at the TAUS Global Content Conferences & Exhibits, one of the top localization industry conferences in the U.S.

Language I/O first publicly unveiled its neural machine translation (NMT) acceleration solution during the LocWorld Process Innovation Challenge in Silicon Valley in November 2019. 

“Early on in our business, we considered building our own NMT solution,” said Language I/O Co-CEO Heather Morgan Shoemaker. “We could have started with the amazing OpenNMT provided by Systran and continued building from there, but Systran already does a great job. As does Google. As does Microsoft. As does DeepL. So why reinvent the wheel? Our strategy? Use ALL OF THE NMT ENGINES. That’s right, we’ve integrated with the best NMT engines in the world in order to provide the best NMT service in the world for customer support translation.” 

So instead of reinventing the wheel and creating a new NMT solution, Language I/O uses the best machine translation solutions that already exist to provide outstanding, fast, accurate translations to its customers in more than 150 languages. In addition to pulling from the best existing NMT engines, Language IO’s technology also incorporates feedback from customer service agents, linguists and customers (the end user). These feedback loops result in the highest possible quality machine translation because they are used to teach the Language I/O machine learning model, literally the brains behind the ground-breaking NMT acceleration tech. 

“A surprisingly large number of our now-customers come to us after they have tried to code their own integrations with one of these NMT engines for chat or email translation,” Shoemaker said. “Every time, they find found that they have many, many company-specific terms that a general NMT engine won’t properly translate. They could train these engines to properly translate their specific terminology, but when you support 10 or more languages and have to train per language pair, that's 20 trainings! For each of these 20 trainings, you’d need 20,000 or more human translated segments just to get started and you’d have to continue to maintain and test the trained engines over time, or the quality degrades. Even enterprise customers with deep pockets are just saying no.”

To see how this technology works and how it can save multinational corporations up to 40% on customer service costs, sign up for a demo here

The Language I/O team will be at booth 13. If you have a minute, stop by and chat with us about our tech and we’ll donate a tree to the national forest system on your behalf. These donations are part of the LIOGives_Trees campaign. Instead of giving conference attendees conference swag, which isn’t sustainable, Language I/O is partnering with non-profits to donate time, money and service at each conference attended in 2020.