Explanation/Reference:
Explanation:
With the Web Language Model automate a variety of standard natural language processing tasks using state-of-the-art language modeling APIs.
Scenario: Source Documents
Documents must be in a specific format before they are uploaded to the system. The first four lines of the document must contain the following information. If any of the first four lines are missing or invalid, the document must not be processed.
the customer account number

the user who uploaded the document

the IP address of the person who created the document

the date and time the document was created

The remaining portion of the documents contain the content that must be analyzed. Prior to processing by the Azure Data Factory pipeline, the document text must be normalized so that words have spaces between them.
Reference: https://azure.microsoft.com/en-us/services/cognitive-services/web-language-model/