Microsoft has announced new features for their Language Understanding Intelligent Services (the natural language engine that powers Cortana) as it comes into public beta.  New features include Chinese language support, the ability to import and export langage-to-system data as JSON objects, and increased usage of internally built language models.  They have also open sourced the SDK code on GitHub.

For those that don’t remember, Project Oxford is the set of Machine Learning APIs for vision, speech, and facial recognition announced at the Build conference and which power websites like HowOld.NET.  These APIs have now been included into the Cortana Analytics suite and have been expanded to include new features.

  • Chinese language support: Chinese support has been one of our most commonly requested features, and now you can create LUIS applications in English or Chinese. In addition, LUIS correctly processes Chinese utterances that include fragments of English.
  • Application import and export: Now, all of the data you’ve entered into a LUIS application can be downloaded to a JSON object and new applications can be created by importing that JSON object. This allows developers to copy applications, share applications with others and check their applications into source control – for example, to be versioned alongside the code for the client app that calls LUIS.
  • Increased coverage of pre-built models: LUIS provides access to many of the same models that power Microsoft products, and we’ve more than tripled the number of intents and entities available, to 196 from 56.

In addition to the new features added, they’ve also made the source code for the SDKs publicly available on GitHub.

This will enable us to better work with the community and build a more inclusive, robust platform. The repo contains Windows and Android support for face, computer vision and speech APIs, and we are working to onboard the remaining packages as well as increase our SDK offerings in iOS and Node.js, both top requests from developers.  — Machine Learning Blog

For more information, check out the Project Oxford site or this blog post on the Machine Learning Blog.