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.

• ✗

  Sentiment Analysis

  Why it's wrong here

  Sentiment Analysis in Azure AI Language evaluates text and assigns positive, negative, or neutral sentiment scores at the sentence and document level. It relies on the language of the text for its internal models, but it does not output which language that text is written in. If a feedback item is in Spanish, Sentiment Analysis might say it is positive, but it will not tell you that the language is Spanish—so it cannot meet the stated requirement.

  When this WOULD be correct

  A company wants to automatically categorize customer feedback as positive, negative, or neutral to prioritize urgent complaints. Sentiment Analysis would be the correct feature to use.

• ✓

  Language Detection

  Why this is correct

  Language Detection is an Azure AI Language feature that analyzes text and returns a predicted language along with a confidence score, using scripts, character sets, and linguistic patterns. For a multinational company receiving feedback in multiple languages, it directly fulfills the requirement by classifying each message's language, enabling downstream routing or translation. It does not infer meaning or extract structure, but its sole purpose is to identify the language, making it the correct choice.

• ✗

  Key Phrase Extraction

  Why it's wrong here

  Key Phrase Extraction is an Azure AI Language feature that scans text to identify the most relevant words and phrases, typically nouns and noun phrases that represent main topics or concepts. For example, from a complaint about 'delayed shipping,' it would extract 'delayed shipping' as a key phrase, but it returns no information about the language of the source text. The extracted phrases are language-specific, but the feature does not report the language of the input, so it fails to address the requirement.

  When this WOULD be correct

  A company wants to automatically extract the main topics or important terms from customer reviews in English to identify common issues. Key Phrase Extraction would be the correct feature to use.

• ✗

  Named Entity Recognition (NER)

  Why it's wrong here

  Named Entity Recognition (NER) in Azure AI Language identifies and categorizes entities in text, such as people (PERSON), organizations (ORG), locations (GPE), dates, and quantities. It processes text using language-specific models and can even recognize entities across languages, but it does not output the detected language of the input document. For instance, NER might extract 'Paris' as a location, yet it will not state that the text itself is in French, so it is not designed for language identification.

  When this WOULD be correct

  A company needs to extract customer names, product names, and locations from support tickets to populate a database. NER would be the correct feature to identify and categorize these entities.

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