AI-102 Implement natural language processing solutions Practice Test 12 — 15 Questions

Question 1

You are an AI engineer at a global e-commerce company. The company uses Azure AI Language to analyze product reviews in English, Spanish, and French. The current solution calls the sentiment analysis API for each review individually, resulting in high latency and cost. You need to design a new solution that processes reviews in batches, reduces the number of API calls, and still supports multiple languages. The solution must also extract key phrases and detect the language automatically. You have the following options:

Option A: Use the Azure AI Language synchronous API with the 'multi-language' parameter set to true. Send reviews one by one.

Option B: Use the Azure AI Language asynchronous batch API. Combine all reviews into a single batch request, but only for one language at a time.

Option C: Use the Azure AI Language asynchronous batch API. Send a single batch request with all reviews, setting the 'language' parameter to 'multi' to auto-detect language, and specify sentiment analysis, key phrase extraction, and language detection as tasks.

Option D: Use the Azure AI Translator service to translate all reviews to English, then use the Azure AI Language batch API for English-only sentiment and key phrase extraction.

Accepted Answer

Option C. Option C is correct. The asynchronous batch API supports multiple tasks (sentiment, key phrases, language detection) in a single request, and setting language to 'multi' enables auto-detection. This reduces API calls and latency. Option A is wrong because synchronous one-by-one calls increase latency/cost. Option B is wrong because it processes only one language per batch, requiring multiple batches. Option D is wrong because it adds translation cost and latency, and may lose nuances.

Answer

Option B

Answer

Option A

Answer

Option D

Question 2

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 3

You are a solution architect at a media company. The company uses Azure AI Speech to generate subtitles for videos. The current solution uses the batch transcription API and takes several hours to process a 1-hour video. The business requires near-real-time subtitles for live streaming events. You need to design a new solution that provides low-latency transcription. You have the following options:

Option A: Use the batch transcription API with a higher priority queue.

Option B: Use the Speech-to-text REST API for real-time streaming with the Speech SDK.

Option C: Use the Azure AI Language API to transcribe audio from a file.

Option D: Use Azure AI Video Indexer to generate subtitles.

Accepted Answer

Option B. Option B is correct. The Speech SDK with real-time streaming provides low-latency transcription suitable for live events. Option A is wrong because batch transcription is not near-real-time. Option C is wrong because Azure AI Language does not transcribe audio. Option D is wrong because Video Indexer is for indexing, not real-time streaming.

Answer

Option C

Answer

Option D

Answer

Option A

Question 4

A company is building a chatbot using Azure OpenAI Service to handle customer inquiries. The bot sometimes responds with incorrect or fabricated information. The team wants to ground the model responses using their own product documentation stored in Azure Cognitive Search. Which configuration should they implement?

Accepted Answer

Configure Azure OpenAI on your data with Azure Cognitive Search as the data source.. Option B is correct because using Azure OpenAI on your data with Azure Cognitive Search indexes enables Retrieval Augmented Generation (RAG) to ground responses in the company's documents. Option A is wrong because fine-tuning requires labeled data and doesn't guarantee grounding. Option C is wrong because embedding search alone doesn't integrate with the model's response generation. Option D is wrong because semantic ranker improves search relevance but doesn't ground the model's output.

Answer

Use Azure AI Document Intelligence to extract text and generate embeddings, then store them in a vector database for direct similarity search.

Answer

Fine-tune the GPT model on the product documentation dataset.

Answer

Enable the semantic ranker in Azure Cognitive Search to improve the relevance of search results.

Question 5

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 6

A healthcare organization needs to redact personally identifiable information (PII) from patient records before using them for research. They have large volumes of unstructured text in multiple languages. Which Azure AI service should they use?

Accepted Answer

Azure AI Language (PII detection feature). Option B is correct because Azure AI Language's PII detection feature can identify and redact PII across multiple languages. Option A is wrong because Azure AI Document Intelligence is for extracting information from documents, not specifically for PII redaction. Option C is wrong because Azure AI Translator focuses on translation, not PII detection. Option D is wrong because Azure AI Content Safety focuses on harmful content, not PII.

Answer

Azure AI Content Safety

Answer

Azure AI Document Intelligence (formerly Form Recognizer)

Answer

Azure AI Translator

Question 7

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 8

You are building a multilingual customer support chatbot using Azure AI Language. The bot must understand user intents in English, Spanish, and French. You have pre-existing labeled data in English only. The solution should minimize manual labeling effort. Which approach should you recommend?

Accepted Answer

Use the multilingual option in conversational language understanding (CLU) and train on the English data only.. Option A is correct because the multilingual option in conversational language understanding (CLU) allows training on English data and generalizing to other languages without additional labeled data. Option B is wrong because translate-train requires translating the entire dataset, which is extra effort. Option C is wrong because building separate projects for each language increases maintenance and labeling effort. Option D is wrong because Azure AI Translator does not handle intent detection.

Answer

Use Azure AI Translator to detect the language and route to a rules-based intent handler for each language.

Answer

Build a separate CLU project for each language and use the English data to bootstrap labeling with active learning.

Answer

Translate the English labeled data into Spanish and French using Azure AI Translator, then train a separate CLU model per language.

Question 9

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 10

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 11

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 12

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 13

Your company runs a global e-commerce platform. You are building a chatbot using Azure AI Language's conversational language understanding (CLU) to handle customer requests in multiple languages. The bot must support English, German, and Japanese. You have labeled training data in English only. The deadline is tight, and you want to minimize manual labeling. You also need to ensure that the bot can gracefully handle unsupported languages (e.g., French) by directing the user to a human agent. You have access to Azure AI Translator. Which approach should you take?

Accepted Answer

Use a single CLU project with multilingual option enabled, train on English data only. Configure the bot to detect the language of user input; if it is English, German, or Japanese, route to CLU; otherwise, route to a human agent.. Option D is correct because it uses the multilingual CLU model for English, German, and Japanese (the model can predict in those languages without additional labeled data) and uses a language detection step to route unsupported languages to a human agent. Option A is wrong because building separate projects for each language requires labeling in each language, which is not minimal effort. Option B is wrong because translating user input introduces latency and potential translation errors. Option C is wrong because translating the English data and training separate models increases effort and may not work well due to translation quality.

Answer

Use a single CLU project with English data only. Translate the English training data into German and Japanese using Azure AI Translator, then train a single multilingual model by including the translated data.

Answer

Use a single CLU project with English data only. Before calling CLU, translate non-English user input to English using Azure AI Translator. For unsupported languages, detect language and route to human agent.

Answer

Build separate CLU projects for English, German, and Japanese. Label training data in each language by translating the English data using Azure AI Translator.

Question 14

You are developing an Azure AI Language solution to analyze customer support tickets. Each ticket has a subject and a description. You need to automatically classify tickets into categories (e.g., 'billing', 'technical', 'account') and extract the product name mentioned. You have a labeled dataset of 10,000 tickets with category labels and product name annotations. The solution must be cost-effective and easy to retrain as new categories emerge. You want to use a single Azure AI Language resource. Which approach should you use?

Accepted Answer

Use custom text classification for category and custom named entity recognition for product name extraction.. Option C is correct because custom text classification can handle the classification task, and custom NER can extract product names, both within the same Azure AI Language resource. Option A is wrong because the prebuilt NER cannot extract custom product names. Option B is wrong because key phrase extraction may not reliably extract product names. Option D is wrong because conversational language understanding is designed for conversational flows, not single-turn ticket classification.

Answer

Use custom text classification for category and key phrase extraction for product name.

Answer

Use conversational language understanding (CLU) to handle both classification and entity extraction in a single model.

Answer

Use custom text classification for category and prebuilt named entity recognition for product name extraction.

Question 15

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.