How to properly train Microsoft LUIS?


I’m now working with LUIS since late December 2016 and I have detected some patterns that I think can be very useful when training your models. My observations are based on models that served different purposes. I’m not going to show you screenshots of the UI since it recently changed dramatically so I’ll focus more on the features and I guess you’ll find your way in the UI yourself.

Entities and phrase list features

IMHO, entities are the corner stone of a LUIS model. They can help LUIS pairing intents & entities together while allowing the resulting action to benefit from the captured value(s). To take a concrete example, if a user asks this question:

Where to find documentation on SharePoint

Continue reading

Posted in Azure Cognitive Services, NLP | Tagged , , | Leave a comment

SharePoint-hosted QnA versus QnA Maker, how do they compare to eachother


I’ve a little bit tackled this topic in my previous post but I’m now going to elaborate more and come with concrete results. Before making the comparison between a SharePoint-Hosted QnA and QnA Maker, let me describe shortly what QnA Maker is all about.

QnA Maker in a nutshell

Microsoft QnA maker is free (for the time being) and allows an easy integration of existing online FAQs and/or custom set of questions/answers. The QnA is supposed to resolve similar questions to the one stored in its KB and return a relevant answer with a confidence score. QnA Maker offers an API that is very straightforward to consume. The below SWOT recaps my perception of this component for the time being: Continue reading

Posted in Azure, Azure Cognitive Services, NLP, SharePoint Online | Tagged , , , | Leave a comment

LUIS and POS-Tagging, better together to build great bots


I recently wrote a blog post on SharePoint’s nextgen searchbox that showed how to use a bot to query SharePoint instead of using the regular searchbox. As many of you know, SharePoint’s search engine is very powerful but end users will not leverage 10% of the keyword query syntax. The idea of having a bot building such queries automatically by interpreting end users questions and “translating” them into SP queries is a great way of letting end users express their needs in natural language and let the system figure out what they want.

Continue reading

Posted in Azure, NLP | Tagged , , , | 3 Comments

Writing a #cognitive #bot that leverages #luis #azureml and #qna maker


In this blog post, I’m going to show you how to create the boilerplate code & actions to leverage a magic set of tools, namely: the bot framework, LUIS, Azure Machine Learning and the easy-to-use QnA maker.

Before diving into the “how to”, let’s describe the fictional scenario I had in mind for this blog post. We want to write a bot that advises people about the fitness for use of products against usages. So, the bot should be able to answer questions such as: “Is SharePoint suitable for document management?”, “Should I use Yammer for social computing or should I use IBM Connections?”. Here is a demo:

Continue reading

Posted in Azure, NLP | Tagged , , , | Leave a comment

#botframework custom #webchat control secret tip


Following an issue I reported to the GitHub repository, pay attention to use the right secret when working with the custom webchat control. Indeed, if you rebuild this control yourself, you’ll have to enable the DirectLine Channel and use this channel’s secret instead of the webchat one.

At the time of writing, using the webchat channel’s secret works (with a websocket issue depicted in my previous post and in the page targeted by the above pointer), but it seems it’s gonna stop working soon, so it’s better to know it…

Happy Coding!

Posted in Azure | Tagged , , | Leave a comment

#botframework custom #webchat control and #websockets hacks


At the time of writing, the default online webchat control (…) isn’t websocket enabled at all. It seems that Microsoft will change that in a near future but I don’t know about the timing.

However, if you’re in a hurry and need to work with websocket right away, because for instance you know all your users use a company browser that is websocket compliant, then you have the opportunity to build your own webchat control as Microsoft made it available on GitHub. It is pretty straightforward to rebuild you own, just follow the instructions on the GitHub page.

Continue reading

Posted in Azure, NLP | Tagged , , | Leave a comment

Building the nextgen SharePoint search through a BOT and LUIS?


I’ve recently worked on creating a BOT with the Microsoft Bot framework that handles queries from end users expressed in natural language. The BOT leverages #LUIS, Microsoft’s NLP engine, in order to extract entities and semantics our of the queries. At the time of writing, both LUIS and the Microsoft Bot framework are still in preview but they let us envision great possibiliities.

The SharePoint search engine is very powerful as it is fast and highly tunnable. However, most of the times, users simply use it as they use Google or Bing. They don’t know the name of the managed properties we created nor even the out of the box keyword query elements such as isDocument:1, etc.

Continue reading

Posted in Azure, SharePoint, SharePoint Online | Tagged , , , , , | 6 Comments