AI-102 Practice Test 41 — 15 Questions

Question 1

A multinational corporation uses Azure AI Language to analyze customer feedback in multiple languages. The solution must detect the language of incoming text and then perform sentiment analysis. Which approach minimizes latency and cost?

Accepted Answer

Use the sentiment analysis API with multilingual support. Option D is correct because Azure AI Language's multilingual sentiment analysis can detect language and sentiment in one call. Option A is wrong because calling two separate endpoints increases latency and cost. Option B is wrong because Translator is an extra service. Option C is wrong because Azure AI Search is for indexing, not sentiment.

Answer

Use the Translator service to translate text to English, then call sentiment analysis

Answer

Store text in Azure AI Search and use cognitive skills for sentiment

Answer

Call the language detection API followed by the sentiment analysis API

Question 2

A developer is deploying a custom text classification model in Azure AI Language. The model must be accessible via a REST API with low latency. Which TWO actions should the developer take?

Accepted Answer

Obtain the endpoint URL and primary key from Language Studio. Options A and C are correct. Deploying the model as a real-time endpoint is required for low-latency REST API access. Using the correct endpoint and key is also necessary. Option B is wrong because batch processing is not low-latency. Option D is wrong because a 'test' endpoint does not exist. Option E is wrong because export/import is not needed for deployment.

Answer

Use the batch processing API

Answer

Export the model as a Docker container

Answer

Deploy to a test endpoint in the Azure portal

Question 3

You are deploying an Azure AI Language custom text classification model. You need to ensure the model meets performance requirements before promoting it to production. Which two actions should you take? (Choose two.)

Accepted Answer

Evaluate the model on a held-out test set that was not used during training.. Options A and D are correct because evaluating on a held-out test set provides an unbiased performance estimate, and reviewing the confusion matrix helps identify specific misclassifications. Option B is wrong because using the training set for evaluation overestimates performance. Option C is wrong because precision and recall are more informative than just accuracy. Option E is wrong because comparing to a baseline is good practice but not specific to model evaluation before promotion.

Answer

Ensure the model achieves at least 95% accuracy on a cross-validation split.

Answer

Use the training set to compute accuracy and ensure it is above 90%.

Answer

Compare the model's performance to a baseline model that always predicts the most common class.

Question 4

A company is building a bot using Microsoft Copilot Studio (formerly Power Virtual Agents). They want to use Azure AI Language to understand user intents. Which TWO components are required?

Accepted Answer

A Conversational Language Understanding (CLU) app. Option A and Option D are correct. A CLU app is needed for intent recognition, and a Microsoft Copilot Studio bot is the interface. Option B is wrong because QnA Maker is deprecated. Option C is wrong because Azure AI Bot Service is not required if using Copilot Studio. Option E is wrong because Azure AI Translator is for translation, not intent recognition.

Answer

A QnA Maker knowledge base

Answer

An Azure AI Translator resource

Answer

An Azure AI Bot Service bot

Question 5

Your company uses Azure AI Language to analyze customer feedback from surveys. The current pipeline extracts key phrases and sentiment. The data science team wants to identify emerging topics over time, such as new product complaints or feature requests. You need to modify the pipeline to track topic evolution. Which Azure AI Language feature should you enable?

Accepted Answer

Custom text classification. Option C is correct because the health text analytics feature (or general entity linking and relation extraction) is not directly for topic evolution; however, Azure AI Language includes a 'custom text classification' that can be trained to classify documents into topics. But the question asks for 'identify emerging topics over time' – the correct answer is to use the 'custom text classification' with a model that categorizes feedback into topic categories and then track changes over time. However, among the options, the 'entity linking' and 'key phrase extraction' are not designed for topic evolution. The best answer is C because Azure AI Language's 'custom text classification' allows you to define categories and classify documents, enabling trend analysis. Option A (key phrase extraction) can be used to identify key terms but not to group them into topics. Option B (named entity recognition) identifies entities but not topics. Option D (conversation summarization) is for conversations, not survey text. So C is correct.

Answer

Named entity recognition (NER)

Answer

Conversation summarization

Answer

Key phrase extraction

Question 6

A company uses Azure AI Speech to provide real-time transcription for customer support calls. The solution must handle multiple languages and filter out profanity. Which THREE configurations are needed?

Accepted Answer

Set the SpeechConfig.SpeechRecognitionLanguage property. Options A, B, and D are correct. SpeechConfig with source language configuration, profanity filter settings, and using the Speech SDK with intermediate results are necessary. Option C is wrong because batch transcription is not real-time. Option E is wrong because custom speech models are not required for profanity filtering.

Answer

Use the Batch Transcription REST API

Answer

Deploy a custom speech model for each language

Question 7

Your organization uses Azure AI Language to perform sentiment analysis and opinion mining on product reviews. You notice that the sentiment scores are often neutral even when the review text contains clearly positive or negative opinions. You suspect the model is not capturing the nuances. Which three actions could improve the sentiment analysis accuracy? (Choose three.)

Accepted Answer

Provide more labeled training examples that cover a wider variety of writing styles and sentiments.. Options A, B, and D are correct because adding more training data, using opinion mining, and enabling domain-specific models are proven ways to improve sentiment accuracy. Option C is wrong because key phrase extraction does not directly affect sentiment scoring. Option E is wrong because using only the basic sentiment analysis API is what you already have; it does not improve accuracy.

Answer

Pre-process the text with key phrase extraction to highlight important terms before sentiment analysis.

Answer

Use the basic sentiment analysis API without any customization.

Question 8

You are building a solution to extract custom entities from legal contracts using Azure AI Language. You have a small set of labeled documents. Which two features should you use to build and improve the custom NER model? (Choose two.)

Accepted Answer

Use active learning to automatically suggest new labels from unlabeled documents.. Options A and B are correct because active learning helps label additional data efficiently, and using synonyms improves entity recognition for varied phrasings. Option C is wrong because key phrase extraction is not part of custom NER training. Option D is wrong because prebuilt NER cannot be extended with custom entities. Option E is wrong because orchestration workflow is for intent detection, not NER.

Answer

Use the prebuilt NER model as a base and extend it with custom entities.

Answer

Configure an orchestration workflow to route documents to the best model.

Answer

Extract key phrases from the documents and use them as features.

Question 9

You are an AI developer at a legal firm. The firm uses Azure AI Language to extract entities from legal documents. The current custom NER model is trained on a small dataset and has low accuracy for certain entity types like 'Statute' and 'Case Citation'. You need to improve the model's performance without increasing the labeling effort significantly. You have the following options:

Option A: Add more labeled examples for the underperforming entity types by manually labeling additional documents.

Option B: Use the prebuilt entity recognition model from Azure AI Language and map its outputs to custom entities.

Option C: Enable active learning in the custom NER project and review the suggested labels from the model.

Option D: Train a new model using the Azure Machine Learning automated ML (AutoML) for text classification.

Accepted Answer

Option C. Option C is correct. Active learning suggests uncertain predictions for manual review, focusing effort on the most impactful examples. Option A is wrong because it increases labeling effort significantly. Option B is wrong because prebuilt models may not extract legal-specific entities. Option D is wrong because AutoML is for classification, not NER entity extraction.

Answer

Option D

Answer

Option B

Answer

Option A

Question 10

You are designing a solution to analyze customer call transcripts using Azure AI Language. The solution must extract key phrases, detect sentiment per utterance, and identify the customer's intent (e.g., 'cancel subscription', 'technical support'). The data is stored in Azure Blob Storage and processed in near real-time. Which combination of Azure AI Language features and processing pattern should you use?

Accepted Answer

Use the conversation summarization API (with utterance-level sentiment and key phrase extraction) and an orchestration workflow model that routes to a custom conversational language understanding project for intent detection.. Option D is correct because the conversation summarization API supports utterance-level sentiment and key phrase extraction, and the orchestration workflow model routes intents across different projects. Option A is wrong because the prebuilt conversational language understanding model does not provide sentiment per utterance. Option B is wrong because custom text classification requires separate training and doesn't handle conversation context. Option C is wrong because the prebuilt key phrase extraction API does not provide sentiment analysis.

Answer

Use custom text classification to classify each utterance into intent categories and use the sentiment analysis API on the entire transcript.

Answer

Use the prebuilt key phrase extraction API to identify important terms and the prebuilt sentiment analysis API for overall transcript sentiment, then map intents via a rules-based approach.

Answer

Use the prebuilt conversational language understanding model for intent detection and Azure AI Language sentiment analysis API for utterance-level sentiment, processing each utterance independently via Azure Functions.

Question 11

You are a developer at a large financial institution. The compliance team needs to automatically analyze quarterly earnings call transcripts to extract forward-looking statements (e.g., 'we expect revenue to grow') and flag any that are overly optimistic or lack necessary disclaimers. The transcripts are stored as text files in Azure Blob Storage. You need to design a solution using Azure AI Language services that meets the following requirements: 1) Extract all forward-looking statements from each transcript. 2) For each statement, determine if it contains optimistic language (e.g., 'strong growth', 'excellent performance') and if it includes a disclaimer (e.g., 'this is a forward-looking statement'). 3) Output a structured JSON file per transcript with the statements, optimism score, and disclaimer presence. 4) Minimize development effort and avoid custom machine learning model training. Which approach should you take?

Accepted Answer

Build a custom NER model to extract forward-looking statements, then use a custom text classification model to classify each extracted statement for optimism and disclaimer presence.. Option B is correct because it combines custom NER to extract forward-looking statements and custom text classification to classify each statement for optimism and disclaimer presence, both using Azure AI Language's pre-built capabilities that require only labeling effort. Option A is wrong because the prebuilt entity recognition does not include forward-looking statements as an entity type. Option C is wrong because key phrase extraction cannot identify specific statements, and sentiment analysis gives an overall score, not per-statement. Option D is wrong because question answering is designed for Q&A, not extraction and classification of statements.

Answer

Use the prebuilt named entity recognition (NER) to identify entities related to financial terms, then apply sentiment analysis to the entire transcript to determine overall optimism.

Answer

Use custom question answering to create a knowledge base of typical forward-looking statements and query the transcript for matches.

Answer

Use key phrase extraction to identify important phrases, then run sentiment analysis on each sentence to detect optimism.

Question 12

Your organization runs a popular news website. You want to use Azure AI Language to automatically generate summaries of news articles for the homepage. The summaries must be concise (under 100 words), extractive (selecting key sentences from the article), and available in both English and Spanish. You have a large corpus of articles in both languages. You need to implement a solution that requires minimal custom development and leverages Azure AI Language's prebuilt capabilities. Which approach should you take?

Accepted Answer

Use the prebuilt extractive summarization API in Azure AI Language for both languages, specifying the maximum summary length.. Option A is correct because Azure AI Language's prebuilt extractive summarization supports multiple languages, including English and Spanish, and can be configured to output concise summaries. Option B is wrong because extractive summarization is a prebuilt feature, not a custom model. Option C is wrong because abstractive summarization generates new sentences, not extractive. Option D is wrong because conversational summarization is designed for multi-turn conversations, not news articles.

Answer

Train a custom extractive summarization model using Azure AI Language's custom text summarization feature with labeled data in both languages.

Answer

Use the conversation summarization API to summarize each article.

Answer

Use the prebuilt abstractive summarization API to generate summaries.

Question 13

You are building a solution to analyze customer feedback from multiple sources: emails, chat logs, and survey responses. You need to detect the overall sentiment trend over time and identify the most frequently mentioned topics. The solution must also allow the business analyst to ask natural language questions about the data (e.g., 'Show me complaints about shipping in the last month'). You have all data in Azure Blob Storage. You need to implement a solution with minimal custom code. Which combination of Azure services should you use?

Accepted Answer

Use Azure AI Language to extract sentiment and key phrases, then index the data in Azure Cognitive Search with semantic search enabled; use the search's built-in features for trend analysis and natural language queries.. Option C is correct because Azure AI Language can perform sentiment analysis and key phrase extraction, and Azure Cognitive Search with semantic ranker can enable natural language querying over the indexed data. Option A is wrong because Azure OpenAI Service alone does not provide built-in analytics over stored data. Option B is wrong because Power BI is for visualization, not natural language querying over text. Option D is wrong because Azure AI Language's question answering is for FAQ, not for querying indexed data.

Answer

Use Azure OpenAI Service to analyze sentiment and generate summaries, and store results in a Cosmos DB for querying.

Answer

Use Azure AI Language to perform sentiment analysis and key phrase extraction, then load the results into Power BI for trend analysis and natural language Q&A.

Answer

Use Azure AI Language's custom question answering to create a knowledge base from the feedback and allow natural language queries.

Question 14

A legal firm is using Azure AI Language to analyze contracts. They need to extract key clauses, parties involved, and dates. The solution must be customizable to their specific contract types. Which TWO Azure AI Language features should they use?

Accepted Answer

Prebuilt NER for Legal. Custom NER allows extracting custom entities like specific clause types and party names. Prebuilt NER for Legal provides out-of-the-box legal entity recognition. The other options are not suitable: Conversation summarization is for chat logs; Key phrase extraction is too generic; Entity linking is for linking to knowledge bases.

Answer

Conversation summarization

Answer

Key phrase extraction

Answer

Entity linking

Question 15

Your organization has a knowledge base of technical manuals in PDF format. You need to enable users to ask natural language questions and get answers from the manuals. Which solution should you build?

Accepted Answer

Azure AI Language custom question answering with the documents as sources. Option B is correct because custom question answering (from Azure AI Language) is designed for FAQ-like Q&A over documents. Option A is wrong because Azure AI Search alone does not provide Q&A. Option C is wrong because Document Intelligence only extracts text. Option D is wrong because Azure OpenAI can do Q&A but requires careful grounding; custom question answering is more straightforward for this use case.

Answer

Azure AI Search with integrated vectorization and semantic search

Answer

Azure OpenAI Service with GPT-4o and Azure AI Search as a data source

Answer

Azure AI Document Intelligence to extract text and then use Azure AI Search