AI-102 Question #210: Real Exam Question with Answer & Explanation

Question

Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution. After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen. You are building a chatbot that will use question answering in Azure Cognitive Service for Language. You have a PDF named Doc1.pdf that contains a product catalogue and a price list. You upload Doc1.pdf and train the model. During testing, users report that the chatbot responds correctly to the following question: What is the price of <product>? The chatbot fails to respond to the following question: How much does <product> cost? You need to ensure that the chatbot responds correctly to both questions. Solution: From Language Studio, you create an entity for cost, and then retrain and republish the model. Does this meet the goal?

Options

• AYes
• BNo

Explanation

The chatbot fails to answer about product stock because a static PDF catalog typically lacks real-time inventory information, which question answering models cannot infer from the document alone.

Common mistakes.

• A. The question 'Do you have <product> in stock?' requires information that is dynamic and external to a static PDF document. Simply training the model on the PDF will not enable it to answer questions about real-time stock availability, as that data is not present within the document itself.

Concept tested. Limitations of document-based question answering for dynamic external data

Reference. https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/overview

No community discussion yet for this question.