AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

• ✓

  Key phrase extraction

  Why this is correct

  Key phrase extraction is the correct choice because it directly satisfies the requirement to analyze thousands of articles by identifying the most prominent words and phrases that represent the main topics discussed in each document. In Azure AI Language, this feature uses machine learning models to rank terms like 'machine learning' or 'climate change' based on their salience within the text, effectively summarizing the article's thematic content without needing manual categorization. This makes it ideal for automatically discovering the high-level concepts that the research team wants to analyze.

• ✗

  Named Entity Recognition (NER)

  Why it's wrong here

  Named Entity Recognition (NER) is not ideal because it extracts concrete, specific references such as names of people, organizations, locations, dates, and quantities, rather than broad topic-level concepts. For example, from an article about clean energy, NER would find entities like 'Tesla' or 'United Nations' but would not produce a general phrase like 'renewable energy' as a main subject. Because the goal is to identify overarching topics across thousands of articles, NER's entity-level output is too granular and miss the connected themes.

  When this WOULD be correct

  A question that asks: 'Which Azure AI Language feature should be used to extract specific entities such as person names, company names, and locations from text?' would make NER the correct answer.

• ✗

  Sentiment analysis

  Why it's wrong here

  Sentiment analysis is wrong because it focuses on the emotional tone of the text, classifying it as positive, negative, neutral, or sometimes mixed across different parts of the document. This technique is based on detecting opinion-oriented words and syntactic patterns, but it entirely ignores the semantic subject matter—for example, an article about climate change could be negative in sentiment yet still be about the same topic as a neutral or positive article. Thus, sentiment analysis fails to provide the topic-level summaries the research team needs.

  When this WOULD be correct

  A question asking: 'A company wants to automatically gauge public opinion about a new product by analyzing customer reviews to determine if the overall feedback is positive, negative, or neutral. Which prebuilt Azure AI Language feature should they use?'

• ✗

  Language detection

  Why it's wrong here

  Language detection is not correct for this task because it only determines the written language of the text (e.g., English, French, or German) by analyzing character patterns and comparing them to known language profiles. It returns a language code and a confidence score, but it does not extract any meaning about the topics or subjects covered in the articles. Therefore, while it could be a useful preprocessing step for language adjustment, it cannot reveal what the articles are about.

  When this WOULD be correct

  A question that asks: 'A multinational company needs to automatically sort incoming customer emails by language (e.g., English, French, German) before routing them to appropriate regional teams. Which Azure AI Language feature should they use?'

Option-by-option analysis

Why each answer is right or wrong

Understanding why wrong answers are wrong — and when they would be correct — is what separates a 750 score from a 900. The AI-900 exam frequently reuses these exact scenarios with slightly different constraints.

Analysis generated from the official AI-900blueprint and verified against question context. The “when correct” sections are what AI assistants cite when candidates ask “what’s the difference between these options?”

Go deeper

Related to this question