A law firm's document review team has 20,000 signed contracts as plain text and wants an automated step that scans each contract and pulls out structured items such as company names, monetary amounts, and effective dates, so paralegals can populate a tracking spreadsheet without reading every page. Which Azure AI Language capability fits this need?
Select an answer to reveal the explanation.
Short Explanation
Notice what the paralegals actually want out of each contract: not a general sense of what it's about, but specific, structured items, a company name here, a dollar figure there, an effective date somewhere else, ready to drop into a spreadsheet. That's a job for a capability built to spot and label those exact kinds of things inside a wall of text. Checking whether the writing sounds positive or negative doesn't help fill in a spreadsheet of names and amounts, that's answering a totally different question. Figuring out what language a document is written in tells you nothing about the contents once you already know it's in English. And condensing the whole contract into a short paragraph might drop the very dollar amount or date someone needed, since a summary isn't built to guarantee every specific detail survives. What's needed is a tool that hunts for and labels specific structured facts, not one that judges tone, identifies language, or shortens the text.
Full Explanation
The correct answer is B. Named entity recognition identifies and categorizes specific structured items within text, such as organization names, monetary values, and dates, which is exactly what the paralegals need extracted into a tracking spreadsheet. Option A is incorrect because sentiment analysis measures whether text expresses a positive, negative, or neutral tone, which has no bearing on pulling out company names or dollar figures from a contract. Option C is incorrect because language detection simply identifies which language a piece of text is written in and does not extract any structured details from within the document. Option D is incorrect because text summarization condenses a document into a shorter overview of its content, which would not reliably surface every specific entity like a dollar amount or an effective date in a structured, extractable form. Since the team needs specific categories of structured information pulled out of unstructured contract text, named entity recognition is the right capability.