E.g., 09/29/2020
E.g., 09/29/2020

XTM International unlocking the secrets of language translation with Inter-language Vector Space

Inter-language Vector Space


XTM International


Friday, 7 August, 2020

XTM International, developers of the XTM Cloud enterprise cloud-based translation management system, has just launched a new neural network-based technology called Inter-language Vector Space. This innovative AI-based technology works out the probability of target words and phrases being equivalent to source words and phrases. Regarded as the next big thing in the language AI area since neural machine translation, it is based on enormous amounts of Big Data for over 250 languages, making up over 31,000 language pairs.

The recent developments in Natural Language Processing (NLP) and neural network modelling, as well as significant investment in building an AI NLP team, have enabled XTM to create Vector Space. This acts as a framework layer upon which XTM can develop AI functionality. Its algorithm-driven automation performs repetitive tasks typically done by translators, reviewers, and post-editors.

“Inter-Language Vector Space is a uniquely new take on L10N AI, which can be likened to the Neural MT breakthrough. It works almost magically allowing for direct alignment at the word and phrase-level for a given segment. A case in point would be the English-Spanish language pair ‘cat’ - ‘gato’, which shows Vector space probability as high as 73% whereas for ‘cat’ - ‘fuego’ the probability plunges to 12%. XTM users will experience the magic first-hand during the bilingual term extraction or translation of texts with inline elements.  We’ve extended the work done by Google and Facebook, adding a new multilingual dimension,” noted Andrzej Zydroń, CTO at XTM International.

Vector Space can be thought of as a set of vectors that each point from one word to another. The process of converting one language into another is equivalent to finding the transformation that converts one Vector Space into the other. Watch the XTM TechTalk with Andrzej Zydroń (CTO) and Dr. Rafał Jaworski (Linguistic AI Expert) to learn more about this process. 

Inter-language Vector Space underpins the current AI functionality in XTM Cloud including auto-alignment, auto-placement of inline elements (released in XTM Cloud 12.3), and auto-bilingual term extraction (XTM Cloud 12.4 release). In both applications AI does much of the heavy-lifting leading to increased linguistic productivity, time and cost savings as well as enhanced user experience.

Would you like to learn more about Vector Space and what it can do for your business? Reach out to [email protected].
 

About XTM international

XTM International develops XTM, the world’s leading cloud-based translation management solution (TMS) with an integrated Computer-Aided Translation (CAT) and Computer-Aided Review (CAR) tools. It is designed to be scalable, flexible, and agile, with industry open standards at its core.

Focused on streamlining complex localization processes and supply chains, XTM centralizes TM assets for real-time collaboration, maximizing translation reuse. The system incorporates in-context WYSIWYG reviews, LQA tests, alternative translations for transcreation, a mobile app for project managers and a REST API with off the shelf connectors for most CMSs.

XTM’s customers include many of the world’s leading enterprises, across a wide variety of industries. More information is available at the XTM website or to test XTM Inter-language Vector Space, sign up for a fully featured 30 day trial of  XTM Cloud.

 

randomness