Create Question Answering Solutions With Azure AI Language (Part 3)

By Ashwin Venugopal -

 





Improve Question Answering Performance

You can enhance a knowledge base's performance by defining synonyms and using active learning after it has been created and tested.

Use Active Learning

Over time, active learning can assist you in improving your ability to accurately respond to consumer inquiries. People frequently pose questions with similar meanings but different wording. Because it allows you to think of other questions for each question and answer pair, active learning can be useful in circumstances such as these. By default, active learning is enabled.

To use active learning, you can do the following:

Create Your Question and Answer Pairs

For your project, you use Language Studio to build pairs of questions and answers. To upload questions and answers in bulk, you may alternatively import a file.

Review Suggestions

After then, active learning starts to provide different questions for every question in your pairs of questions and answers. From the Review recommendations box, you can access this.

After reviewing the proposed alternative words for each question, you may choose to accept or reject them by clicking the checkmark or delete symbol next to the alternate phrase. The Accept all ideas or Reject all suggestions option at the top allows you to accept or reject suggestions in bulk.

When you choose Add alternate question for a pair in the Edit knowledge base window, you can also manually add alternate questions.

Define Synonyms

When user-submitted queries contain more than one word to convey the same idea, synonyms come in handy. A consumer of a travel agency might use the terms "reservation" or "booking," for instance. By classifying these as synonyms, the question-answering service may identify a suitable response independent of the term used by a specific consumer.

Conclusion

We have successfully learnt about improving question answering performance.

 












Comments

Post a Comment

Popular posts from this blog

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

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

How AMI Store & Restore Works?

By Ashwin Venugopal -
Image
  CreateStoreImageTask The CreateStoreImageTask API stores an AMI as a single object in an S3 bucket. The API initiates a task that collects all the data from the AMI and its associated snapshots, subsequently using an S3 multipart upload to store this data in an S3 object. It gathers all elements of the AMI, including most of the non-Region-specific metadata and all EBS snapshots included in the AMI, and consolidates them into a single object in S3. During the upload process, the data is compressed to minimize the space utilized in S3, which means that the S3 object could be smaller than the total sizes of the snapshots in the AMI. If the account making this API call has access to AMI and snapshot tags, they will be retained. The S3 object shares the same ID as the AMI, except it has a .bin extension. Additionally, the S3 metadata tags for the object include the AMI name, AMI description, AMI registration date, AMI owner account, and a timestamp indicating when the store operation...
Read more