Project Oxford Extends Reach
Project Oxford Extends Reach
Written by Alex Armstrong   
Monday, 09 November 2015

Microsoft Research has provided a public beta of LUIS, Language Understanding Intelligent Service, the fourth element of Project Oxford. Meanwhile beta versions of the other three SDKs are now available on GitHub.

Project Oxford from Microsoft Research provides pre-trained artificial intelligence services in four categories - Face, Speech, Vision and Language Understanding.  Reporting the announcement of Project Oxford at this year's Build, Mike James explained by this is such a welcome idea:

The big problem with incorporating AI into your own project is that it is not only complicated but time consuming. Even if  you understand the theory to build your own working AI, you need a lot of data and a lot of time spent training it to produce a good performance. Of course, if what you need is something that tackles a standard task, you could use something that had been trained by someone else. 

Examples of using the Face API in apps were quickly forthcoming, see How Old - Fun, Wrong, Potentially Risky? and Twin Detection Using AI. Now, along with the computer vision and speech APIs, the Face Detection and Face Verification client libraries and samples are on GitHub.

The remaining API for creating language understanding models that can be used with the speech API and its intent recognition is the most flexible and technically demanding and up until now has been in invitation only beta.

luis

Now, as announced in a blog post Ryan Galgon, Senior Program Manager in the Technology & Research group at Microsoft, Project Oxford’s Language Understanding Intelligent Service (LUIS) has public beta availability anyone can create an account to create models to understand intents and entities and to deploy them to an HTTP endpoint or to a device. 

Sample code is available to help new users:

luiscode

 

In addition to wider availability of LUIS, Microsoft introduced the following new features:

 

  • Chinese language support: Responding to a common request it is now possible to 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. The number of intents and entities available has more than tripled going from 56 to 196.

 

Galgon writes in his blog post:

Since launch, we’ve worked closely with early adopters on our MSDN forum, and we’ve added bulk import of unlabeled utterances, regular expression machine-learning features, a super-charged date-time entity and a lot of UI polish.

It is to be hoped that widening access to LUIS will also the rapid rate of development will continue, making it ever easier to add language understanding to apps using readily available models.

 

 

 

projoxfordluis

More Information

Microsoft expands availability of Project Oxford intelligent services

Project Oxford

Project Oxford LUIS

Microsoft Project Oxford on GitHub

Related Articles

MIcrosoft's Project Oxford AI APIs For The REST Of Us

How Old - Fun, Wrong, Potentially Risky?

Twin Detection Using AI 

 

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on, Twitter, FacebookGoogle+ or Linkedin.

 

Banner


Find Your 2000-Year-Old Double With Face Recognition
18/02/2017

Wouldn't you like to know if you look like Caesar or Venus? It's now possible thanks to advanced face recognition software. Discover how the Quebec Musée de la Civilisation is using the Betaface [ ... ]



Bitesnap - Applying Deep Learning to Calorie Counting
15/02/2017

Bitesnap is a recently launched mobile app that uses photo recognition to help you control your calorie intake. To learn more, we interviewed Keith Ito, one of the app's core developers to discuss Bit [ ... ]


More News

 

 
 

 

blog comments powered by Disqus

Last Updated ( Monday, 09 November 2015 )
 
 

   
Banner
RSS feed of news items only
I Programmer News
Copyright © 2017 i-programmer.info. All Rights Reserved.
Joomla! is Free Software released under the GNU/GPL License.