AI-103 Text Analysis Practice Test 2 — 15 Questions

Question 1

You are writing code that submits a sentiment analysis request to the Azure AI Language analyze-text endpoint. The response for each document includes a sentiment value and confidence scores for positive, neutral, and negative. A colleague asks what the top-level sentiment value represents when the document mixes praise and criticism. What should you tell them?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

It is the label with the highest confidence score across the document's sentences, recalculated as a document-level aggregate.. The analyze-text sentiment response provides a document-level sentiment label plus positive, neutral, and negative confidence scores, alongside per-sentence assessments. For mixed documents, the document label reflects the polarity that dominates the combined sentence evidence, so it is not tied to position, length, or a simple numeric averaging rule.

Answer

It is a numeric average of the sentence confidence scores converted into a single polarity band by fixed thresholds.

Answer

It is the sentiment of the longest sentence, since that sentence is assumed to carry the most information.

Answer

It is always the sentiment of the first sentence, because the service anchors the document result to the opening statement.

Question 2

Your development team is building a global customer support portal. Incoming tickets arrive in dozens of different languages. You need to automatically route tickets to the correct regional team based on the language of the ticket text. Which Azure AI Language feature should you call?

Accepted Answer

Language detection. Language detection is the Azure AI Language feature specifically designed to identify the language of a given text and return the detected language name and ISO 639-1 code. For routing tickets based on language, this is the exact capability needed. Sentiment analysis, NER, and key phrase extraction serve different purposes and do not identify language.

Answer

Sentiment analysis

Answer

Named Entity Recognition (NER)

Answer

Key phrase extraction

Question 3

You are calling the Azure AI Language REST API for Named Entity Recognition (NER) and receive an HTTP 429 status code. How should your application handle this error?

Accepted Answer

Implement an exponential backoff retry policy and resend the request after a delay.. HTTP 429 indicates 'Too Many Requests', meaning you have exceeded the rate limit or quota for the Azure AI Language service. The correct handling is to implement an exponential backoff retry policy, which gradually increases the delay between retries to avoid overwhelming the service. This is a standard practice for transient throttling errors.

Answer

Switch the API endpoint to use the Free pricing tier.

Answer

Regenerate the subscription key and restart the client service.

Answer

Immediately re-submit the request with doubled payload size.

Question 4

You are processing medical intake forms using Azure AI Language. You need to identify and categorize medical terms, medications, and dosages. Which feature should you use?

Accepted Answer

Health text analytics. Health text analytics in Azure AI Language is specifically designed for the medical domain and can identify medical entities such as medications, dosages, diagnoses, and symptoms. It goes beyond generic NER by recognizing healthcare-specific terminology and relationships. This makes it the correct choice for processing medical intake forms where medications and dosages must be categorized.

Answer

Key phrase extraction

Answer

Standard Named Entity Recognition (NER)

Answer

Custom text classification

Question 5

You need to extract key concepts and main ideas from long-form technical support articles using the Azure AI Language service. Which feature should you invoke?

Accepted Answer

Key phrase extraction. Key phrase extraction is the Azure AI Language feature designed to identify the main concepts and important terms from unstructured text. It analyzes the text and returns a list of key phrases that represent the core ideas, making it ideal for extracting key concepts from long-form technical support articles. Summarization, while related, produces a condensed version of the text rather than a list of key phrases, and is typically used for creating abstracts or summaries. Therefore, key phrase extraction directly fulfills the requirement to extract key concepts and main ideas.

Answer

Personal Personally Identifiable Information (PII) detection

Answer

Language detection

Answer

Summarization

Question 6

You are building an application that analyzes user feedback. You need to detect instances where users share their phone numbers, email addresses, and credit card numbers so that you can automatically redact them. Which feature should you use?

Accepted Answer

PII detection. PII detection in Azure AI Language is specifically designed to identify and redact personally identifiable information such as phone numbers, email addresses, and credit card numbers. It returns the detected entities along with their categories and confidence scores, enabling automatic redaction. This is the exact feature needed for the scenario.

Answer

Sentiment analysis

Answer

Language detection

Answer

Named Entity Recognition (NER)

Question 7

You are configuring text summarization using the Azure AI Language REST API. You need to generate a summary that consists of a few distinct sentences pulled directly from the source document without altering their wording. Which summarization kind should you specify?

Accepted Answer

Extractive summarization. Extractive summarization produces a summary composed of sentences taken verbatim from the source document, preserving original wording. This exactly matches the requirement to pull distinct sentences without altering them. Abstractive summarization would rephrase and generate new text, which violates the constraint.

Answer

Key phrase extraction

Answer

Abstractive summarization

Answer

Custom single-label classification

Question 8

You are configuring an Azure AI Language resource in the Azure portal. You need to ensure that the text analysis solution supports custom text classification and named entity recognition. Which pricing tier should you select?

Accepted Answer

Standard (S). The Standard (S) pricing tier for Azure AI Language supports custom text classification and custom named entity recognition (NER). The Free (F0) tier does not support these custom features. Therefore, you must select Standard (S).

Answer

Premium (P1)

Answer

Basic (B)

Answer

Free (F0)

Question 9

You are building an app to analyze customer feedback. You want to extract named entities such as people, locations, and organizations. Which Azure AI Language feature should you use?

Accepted Answer

Named Entity Recognition (NER). Named Entity Recognition (NER) is the Azure AI Language feature specifically designed to identify and categorize entities like people, locations, organizations, and more from unstructured text. It returns both the entity text and its type (e.g., Person, Location, Organization), which directly matches the requirement to extract named entities from customer feedback. Other features like sentiment analysis or key phrase extraction do not provide entity type classification.

Answer

Language detection

Answer

Sentiment analysis

Answer

Key phrase extraction

Question 10

You are using Azure AI Language custom text classification. You have uploaded your training dataset and trained a model. You notice that your evaluation metrics show low precision. What does low precision indicate about your model?

Accepted Answer

Many of the items predicted as a specific class actually belonged to a different class.. Low precision indicates that when the model predicts a class, it is often incorrect—meaning many predicted positives are false positives. In other words, items predicted as a specific class actually belong to a different class. This is the definition of low precision.

Answer

The model failed to find many actual positive instances in the dataset.

Answer

The latency of the REST API calls is too high.

Answer

The training dataset contained fewer than 5 documents per class.

Question 11

You are implementing opinion mining as part of sentiment analysis in Azure AI Language. An incoming review states, 'The room was spacious, but the staff was rude.' What does opinion mining return for this sentence?

Accepted Answer

Aspect targets ('room', 'staff') along with their corresponding evaluations ('spacious', 'rude') and individual sentiments.. Opinion mining in Azure AI Language returns aspect-based sentiment analysis, identifying aspect targets (e.g., 'room', 'staff') and their corresponding evaluations (e.g., 'spacious', 'rude') with individual sentiment polarities. For the given review, it would return 'room' as positive and 'staff' as negative, providing granular insights beyond document-level sentiment.

Answer

A binary classification indicating whether the review is spam or genuine.

Answer

A single neutral sentiment score for the entire document.

Answer

A translated version of the review in English.

Question 12

You are migrating an existing solution from the legacy Text Analytics API v3.1 to the current Azure AI Language REST API. You notice changes in the JSON request body structure. Where should the document text array now be nested in the payload for a sentiment analysis request?

Accepted Answer

Nested inside an 'analysisInput' object under the root.. In the current Azure AI Language REST API (formerly Text Analytics), the request body for sentiment analysis nests the documents array inside an 'analysisInput' object at the root. The structure is: { "analysisInput": { "documents": [ { "id": "1", "text": "...", "language": "en" } ] }, "parameters": { ... } }. This change from the legacy v3.1 API, where documents were directly under the root, reflects a more organized payload with separate sections for input and parameters.

Answer

Inside the HTTP header as a base64 encoded string.

Answer

Directly under the root object as a 'documents' array.

Answer

Nested inside a 'parameters' object.

Question 13

You need to evaluate customer reviews to determine whether the overall tone is positive, negative, or neutral. Which Azure AI Language feature should you use?

Accepted Answer

Sentiment analysis. Sentiment analysis is the Azure AI Language feature that evaluates text and returns a sentiment label (positive, negative, neutral, or mixed) along with confidence scores. It is specifically designed to determine the overall tone of customer reviews. The other features do not provide sentiment scoring.

Answer

Language detection

Answer

Named Entity Recognition

Answer

Key phrase extraction

Question 14

You are using Language Studio to build a custom named entity recognition (custom NER) project. You have tagged your training data and successfully trained your first model. You want to test the model interactively without writing code. Which tool in Language Studio should you use?

Accepted Answer

Test model pane. In Language Studio, after training a custom NER model, you can test it interactively using the 'Test model' pane. This pane allows you to input text and see the model's predictions without writing any code. It is specifically designed for quick validation and debugging.

Answer

Deployment settings

Answer

Data labeling page

Answer

Model performance tab

Question 15

You are creating a Language resource in the Azure portal. Which blade should you navigate to if you need to retrieve your endpoint URL and subscription keys for your application configuration?

Accepted Answer

Keys and Endpoint. The 'Keys and Endpoint' blade in an Azure AI Language resource provides the endpoint URL and the subscription keys (Key1 and Key2) required for authenticating client applications. These credentials are essential for configuring your application to call the Language service APIs. This blade is specifically designed to surface the connection information needed for development and integration.

Answer

Diagnostic settings

Answer

Pricing tier

Answer

Access control (IAM)