Create a Custom Text Classification Solution

By Ashwin Venugopal -

 





Introduction

You may process natural language for your own application by using the Azure AI Language service.

One of the most prevalent AI issues is Natural Language Processing (NLP), which requires software to perceive voice or text in the same way that people do. Text classification is a component of Natural Language Processing (NLP), and Azure offers methods for text classification that include sentiment, language, and user-defined custom categories.

Understand Types of Classification Projects

Text files are given labels by custom text classification, which in the Azure AI Language service is a class that the developer defines. A video game synopsis, for instance, could be categorized as "Adventure," "Strategy," "Action," or "Sports."

Custom text classification falls into two types of projects:

  • Single Label Classification - you can assign only one class to each file. Following the above example, a video game summary could only be classified as "Adventure" or "Strategy".

  • Multiple Label Classification - you can assign multiple classes to each file. This type of project would allow you to classify a video game summary as "Adventure" or "Adventure and Strategy".

When creating your custom text classification project, you can specify which project you want to build.

Single vs. Multiple Label Projects

The main distinctions between multiple label classification projects are labeling, model improvement considerations, and the API payload for classification activities, in addition to the capacity to classify files into many categories.

Labeling Data

In single label projects, each file is assigned one class during the labeling process; class assignment in Azure AI Language only allows you to select one class.

You can designate as many classes as you like for each file when labeling several label projects. Your data must maintain clarity and offer a good distribution of potential inputs for your model to learn from due to the impact of the additional complexity.

You can designate as many classes as you like for each file when labeling several label projects. Your data must maintain clarity and offer a good distribution of potential inputs for your model to learn from due to the impact of the additional complexity.

Labeling data correctly, especially for multiple label projects, is directly correlated with how well your model performs. The higher the quality, clarity, and variation of your data set is, the more accurate your model will be.

Evaluating and Improving Your Model

The number of accurate predictions is only one aspect of evaluating your model's predictive ability. When the model predicts a label x and the actual label is x, the classification is correct. In the actual world, incorrect classifications lead to various types of inaccuracies in documents:

  • False positive - model predicts x, but the file isn't labeled x.
  • False negative - model doesn't predict label x, but the file in fact is labeled x.

With a single label project, you can identify which classes aren't classified as well as others and find more quality data to use in training your model. For multiple label projects, figuring out quality data becomes more complex due to the matrix of possible permutations of combined labels.

API Payload

Azure AI Language provides a REST API to build and interact with your model, using a JSON body to specify the request. This API is abstracted into multiple language-specific SDKs.

Conclusion

We have successfully learnt about types of classification projects.

























Comments

Post a Comment

Popular posts from this blog

Azure AI Search plugin in Microsoft Security Copilot (Preview)

By Ashwin Venugopal -
Image
  Introduction Azure AI Search is a service that allows to reliably extract content search, extract, and understand at scale. It is typically used to search for documents, data surveys, and chat-style Copilot apps over proprietary data. Indexing and querying are Azure AI Search's two main workloads. While querying allows to search the content from index, indexing loads the content into the search engine and makes it searchable. By connecting to one of the Azure AI Search indexes from within Copilot, the Microsoft Security Copilot integration for Azure enables to use the content in Copilot to produce contextualized, pertinent, and targeted responses.  Requirement Before using the Azure AI Search plugin in Copilot, the desired Azure AI Search index to connect to Copilot is configured as follows: The text field must be searchable.  The title field must be filterable. The vector-field must use text-embedding-ada-002. Integrated vectorization can be used to setup an index in t...
Read more

Information Protection Scanner: Resolve Issues with Information Protection Scanner Deployment

By Ashwin Venugopal -
Image
  About If you are experiencing problems with the Microsoft Purview Information Protection scanner, check the health of your deployment by utilizing the Start-ScannerDiagnosticsPowerShell cmdlet to start the scanner diagnostic tool. The diagnostics tool checks the following details and then creates a log files with the results: Whether the database is up to date. Whether network URLs are accessible. Whether there's a valid authentication token and policy can be acquired. Whether the profile is defined in the Azure portal. Whether offline/online configuration exists and can be acquired. Whether the rules configured are valid.  The Start-ScannerDiagnostics command does not perform a comprehensive check of prerequisites. If you encounter problems with the scanner, you need to verify that your system meets the scanner's requirements, and that your scanner's configuration and installation are finished.  Verify Scanning Details Per Scanner Node and Repository Run the Get-ScanSt...
Read more

Threat Hunting in Microsoft Sentinel (part 1)

By Ashwin Venugopal -
Image
  To read part 2, please click  here To read part 3, please click  here Introducing the Microsoft Sentinel Hunting Page Threat hunting is a series activities performed while investigating and as there are no guidelines to perform it, the available tools on the Microsoft Sentinel can be introduced to perform better in your investigations. Firstly, you have to choose the Hunting link in the Microsoft Sentinel navigation menu to get to the Hunting page which is divided into the following sections: The header bar- It is located at the top of the page as usual and contains Refresh as well as timespan drop down menu. The New Query button can help you with creating a new query and the Run all queries button can run all the hunting queries in the background while also updating the hunting query list section with the number of results found.  The summary bar- Here, you can view the total number of queries available to run, the total number of bookmarks, the number of result...
Read more