The Microsoft Syntex AI model type Structured Document Processing model (previously known as Forms Processing) has had some significant updates which were launched as part of Microsoft Syntex. In my opinion the biggest update is Structured Document Processing models now allows models to be reused across libraries and sites.
A new Microsoft Syntex AI document processing model was recently released called freeform which purpose is to automatically extract information from unstructured and freeform documents such as letters, contracts or correspondence. Initially I was a little confused with the new freeform model type and what scenario you would use it for, so I needed to test it out & learn. My key confusion was what exactly are "freeform" documents and seeing which documents would work best with the model? I will attempt to answer this question in this blog along with introducing the freeform model and other Syntex model renaming changes.
SharePoint Syntex now makes extensive use of the Term Store (Managed Metadata Services - MMS) and does so in many different ways which I will go through in this blog. When Microsoft were working on Project Cortex and before SharePoint Syntex & Viva Topics were even known, there was a big investment by the SharePoint engineering team to improve the term store. The term store when moved to SharePoint online from SharePoint on-premise was literally moved "as is" (I believe!) to the cloud by Microsoft and it came with the old slow modern UI. Adding/administering terms took ages as users had to wait for often long periods of time whilst navigating between terms, adding terms etc. It was sometimes very painful so some people would even avoid using the termstore altogether and lose the benefit to provide a unified set of terms to apply to content in Microsoft 365 that can be reused between sites/libraries. So it was great that in early 2020 Microsoft announced they had modernised the Term Store - I was instantly curious how this was going to be utilised in Project Cortex as little was still known about it.
Over the past few months there have been a number of SharePoint Syntex updates with the purpose to more closely integrate with Viva Topics. Before this the two products have been quite separated which has been odd especially as they were born from the same Project (Cortex). This blog will focus on using Syntex to generate Viva Topics.
rule to specify to remove duplicate entities, extract only a certain number of values or lines from the entity extractor value. This happens at the same time the entity extractor is invoked on the document and allows greater control of the returned values. There is a new Refine extracted info button now available in the entity extractors section of a document understanding model.
New SharePoint Syntex functionality has recently arrived in my tenant to extend the Advanced Search functionality that is available in document libraries to allow custom columns from your Syntex models…
A new update has recently came to SharePoint Syntex to allow users to create & train their own local document understanding models in Team or Communication sites. The models can…