Question Answering Alternative Phrasing vs Entities

Implement custom language models
Answer Correct answer: B — Creating an entity for cost does not resolve the question phrasing mismatch in Azure question answering.

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 ? The chatbot fails to respond to the following question: How much does 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?

  1. Yes
  2. No Correct Answer

Community Votes

B
100%

100% of anonymous learners picked answer B. Votes are pick records left by other test-takers — they are not the verified answer.

Community Insight

This question tests the distinction between entities and alternative phrasing in Custom Question Answering; the common trap is assuming entities can bridge question phrasing gaps.

Creating an entity for a term like cost does not resolve question phrasing mismatches in Azure Cognitive Service for Language. This page establishes that adding alternative phrasing to the question and answer pair is the correct method to handle varied user queries.

Choosing Yes because adding an entity seems like a way to capture synonyms, but entities extract data from text rather than matching alternative question structures.

Community Discussion (3 comments)

Murtuza 👍 6
Solution: From Language Studio, you add alternative phrasing to the question and answer pair, and then retrain and republish the model. Choice is B
syupwsh 👍 1 Selected: B
No is CORRECT. Creating an entity for "cost" and retraining the model is unlikely to resolve the issue of the chatbot failing to respond to variations in the phrasing of the question. The problem is likely due to the model not being trained adequately on diverse question patterns. To address this, you would need to add variations of the questions (e.g., "How much does cost?") to the training data and retrain the model. This will ensure the model is better equipped to handle different phrasings of the same question.
mustafaalhnuty 👍 1 Selected: B
B 100%

Comments & Corrections

No comments yet — spotted an error or have a note? Share it below.

Log in to comment, report an error, or add a note about this question.

Submitted for moderation before publishing. Keep it helpful and respectful.

Expert Analysis

Why the Answer Is Correct

The correct answer is No because creating an entity for "cost" does not address the root cause of the failure. In Azure Custom Question Answering, entities are used to extract specific data points from an answer or to add synonyms for entity values, not to map alternative question phrasing to an existing answer. The chatbot fails because it does not recognize "How much does cost?" as a valid question pattern for the existing answer.

Why the Other Options Are Wrong

Option A (Yes) is incorrect because it misunderstands the function of entities in question answering. Entities do not bridge the gap between different question structures like "What is the price" and "How much does cost". To fix this, you must explicitly add alternative phrasing to the question and answer pair so the model learns the new pattern.

Community Comment Notes

Commenters correctly identified that creating an entity for "cost" is "unlikely to resolve the issue of the chatbot failing to respond to variations in the phrasing of the question". As Murtuza noted, the correct solution involves adding "alternative phrasing to the question and answer pair" rather than creating an entity.

Official Reference

Exam Strategy

When a question answering chatbot fails on a differently phrased question, the solution is almost always to add an alternate question phrasing to the knowledge base. Do not confuse entities, which extract data, with question variations.

Related Analysis

← Back to AI-102 Study Guide