Announcing GA of Text Analytics for health, Opinion Mining, PII and Analyze

This post has been republished via RSS; it originally appeared at: New blog articles in Microsoft Tech Community.

Text Analytics v3.1 is in GA!

 

It has been a year since we released (in GA) our last TA API (v3.0). After five previews of adding features, responsible AI, incorporating customer feedback, UX feedback, and optimizations; in July 2021 we announced GA (General Availability) of Text Analytics v3.1. With this release, starting July 2021 customers can use Text Analytics for health, Opinion Mining, PII and Analyze as GA offerings.

 

GA of Text Analytics for health

 

Text Analytics for health is a feature of the Text Analytics API service that extracts and labels relevant medical information from unstructured texts such as doctor's notes, discharge summaries, clinical documents, and electronic health records. Millions of Text Records were processed during the preview in the last year. (1 text record = 1000 characters). Here is how the output from Text Analytics for health can be used to identify entities, extract and link relations and detect assertions. 

 

health-relation-extraction.png

There are two ways to utilize this service:

A blog about the announcement is published here.

 

GA of Opinion Mining

 

Opinion Mining is a feature of Sentiment Analysis. Also known as Aspect-Based Sentiment Analysis in Natural Language Processing (NLP), this feature provides more granular information about the opinions related to words (such as the attributes of products or services) in text. More than a 100 customer have tried the previews and continue to use it across the globe. Here is how the output of Opinion mining can be used to deep dive in to actionable sentiments.

 

opinion-mining.png

 

More details are available here.

 

GA of PII (Personally Identifiable Information and Redaction)

 

The PII feature is part of Named Entity Recognition (NER), and it can identify and redact sensitive entities in text that are associated with an individual person such as: phone numbers, email addresses, mailing addresses, passport numbers. 100s of customers have tried the previews and continue to use it across the globe. More details are available here.

 

GA of Analyze (async endpoint)

 

The /analyze endpoint for Text Analytics allows you to analyze the same set of text documents with multiple text analytics features in one API call. Previously, to use multiple features you would need to make separate API calls for each operation. Consider this capability when you need to analyze large sets of documents with more than one Text Analytics feature. More details are available here.

 

All the above offerings along with a demo are also highlighted in the AI Show:

  1. What's new in Text Analytics for Health - YouTube
  2. What’s New in Text Analytics: Opinion Mining and Async API - YouTube

 

References:

You can check the Quickstart, which offers an easy way to get started with any of the Text Analytics offerings.

You can check the Pricing details here.

 

 

Leave a Reply

Your email address will not be published. Required fields are marked *

*

This site uses Akismet to reduce spam. Learn how your comment data is processed.