AI-102 Practice Question: Implement knowledge mining and information extraction solutions
You are using Azure AI Language Service to extract key phrases from customer reviews. You notice that for reviews containing the word 'not good', the service sometimes extracts 'good' as a key phrase. What is the most likely reason?
⚠ Common exam trap
Candidates often assume Azure AI Language Service handles negation across all features, but key phrase extraction explicitly does not consider negation, unlike sentiment analysis which does.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Key phrase extraction does not consider negation
Key phrase extraction in Azure AI Language Service uses a statistical model that identifies significant terms based on frequency and context, but it does not inherently understand negation. When the phrase 'not good' appears, the model may still extract 'good' as a key phrase because it recognizes 'good' as a high-value term, ignoring the negation. This is a known limitation of the feature, as it focuses on noun phrases and important terms rather than sentiment or negated constructs.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
The language detection model misidentified the language
Why it's wrong here
Language detection returns a language code and confidence, and misidentification would garble all extracted phrases, not selectively split negation from its adjective. It is used to route multilingual text to the correct language model, which is the right choice when input language is genuinely unknown.
- ✗
You need to set a confidence threshold to exclude negative phrases
Why it's wrong here
Key phrase extraction returns no per-phrase confidence score, so no threshold can be applied to filter results. Confidence thresholds belong to sentiment analysis, where scores per sentence or document let you suppress low-confidence classifications; that is the correct tool when sentiment polarity, not phrase extraction, is required.
- ✓
Key phrase extraction does not consider negation
Why this is correct
Key phrase extraction identifies statistically significant terms without parsing negation, so 'good' is extracted as a standalone phrase from 'not good'. The model treats words independently rather than understanding that the negation inverts the sentiment.
- ✗
The service is not trained on your specific domain
Why it's wrong here
Key phrase extraction is a pretrained, domain-agnostic model with no custom training capability, so domain adaptation is not available. Custom training applies to custom named entity recognition or custom text classification, which would be correct if you needed domain-specific entity or category labels.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 761-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.