AI-102 Implement natural language processing solutions Practice Test 8 — 15 Questions

Question 1

Your team uses Azure AI Language in a multi-region architecture. You need to ensure that the solution is resilient to regional outages. Which THREE actions should you take?

Accepted Answer

Use a global endpoint that routes to the nearest region. Deploying resources in multiple regions, using a load balancer to distribute traffic, and using a global endpoint provide high availability. Single region and disabling regional endpoints do not improve resilience.

Answer

Disable regional endpoints

Answer

Use a single region with high availability enabled

Question 2

You need to analyze the sentiment of social media posts in real time using Azure AI Language. Which approach should you use?

Accepted Answer

Call the sentiment analysis REST API for each post. Azure AI Language supports real-time sentiment analysis via its REST API. Batch processing is for offline analysis; event hubs and stream analytics are overkill for simple API calls.

Answer

Use Azure AI Search with cognitive skills

Answer

Use the batch processing feature in Azure AI Language

Answer

Send posts to an Event Hub and use Stream Analytics

Question 3

You are building a chatbot that must understand user intents from free-text input. You have a small set of labeled examples. Which Azure AI Language feature should you use to classify intents with minimal effort?

Accepted Answer

Conversational Language Understanding (CLU). Conversational Language Understanding (CLU) is the correct service for intent classification from conversational utterances. It supports custom models with minimal data. Custom text classification is for document-level classification, not intents. Language Detection identifies languages, not intents. Entity Linking extracts entities, not intents.

Answer

Entity Linking

Answer

Custom Text Classification

Answer

Language Detection

Question 4

You need to transcribe customer service calls into text for analysis. Which Azure service should you use?

Accepted Answer

Azure AI Speech-to-Text. Azure AI Speech-to-Text is the correct service for converting audio to text. Text-to-Speech does the opposite. Translator translates text. Language Understanding (CLU) interprets intents.

Answer

Conversational Language Understanding

Answer

Azure AI Translator

Answer

Azure AI Text-to-Speech

Question 5

You are deploying a custom Named Entity Recognition (NER) model using Azure AI Language. You have 500 labeled documents. After training, the model shows high precision but low recall. Which action is most likely to improve recall?

Accepted Answer

Add more labeled examples covering the missed entities. Low recall means many true entities are missed. Adding more labeled examples that include the missed entities helps the model learn to recognize them. Increasing training epochs may lead to overfitting. Changing the model to a different type (e.g., CLU) is not appropriate for NER. Reducing the confidence threshold would allow more predictions but could lower precision, and the question targets recall specifically.

Answer

Switch to Conversational Language Understanding

Answer

Reduce the confidence threshold for entity extraction

Answer

Increase the number of training epochs

Question 6

Your application needs to extract key phrases from customer reviews to identify common topics. Which Azure AI Language feature should you use?

Accepted Answer

Key Phrase Extraction. Key Phrase Extraction is the correct feature for extracting key points from text. Entity Recognition extracts named entities. Sentiment Analysis determines sentiment. Language Detection identifies language.

Answer

Sentiment Analysis

Answer

Language Detection

Answer

Named Entity Recognition

Question 7

You are using Azure AI Translator to translate documents from English to French. Some technical terms must remain untranslated. How should you handle this?

Accepted Answer

Provide a dictionary with the terms and their translations set to the same word. Azure AI Translator supports a dictionary to specify words that should not be translated. The 'includeUntranslated' parameter does not exist. Post-editing is inefficient. Using a custom model requires training data.

Answer

Set the includeUntranslated parameter to true

Answer

Train a custom translation model that ignores those terms

Answer

Post-process the output to revert translations of those terms

Question 8

You need to analyze customer feedback to determine whether the sentiment is positive, negative, or neutral. Which Azure AI service should you use?

Accepted Answer

Azure AI Language - Sentiment Analysis. Azure AI Language provides Sentiment Analysis as a built-in feature. Language Detection, Key Phrase Extraction, and NER are different capabilities.

Answer

Azure AI Language - Key Phrase Extraction

Answer

Azure AI Language - Named Entity Recognition

Answer

Azure AI Language - Language Detection

Question 9

You are building a multilingual chatbot using Azure AI Language. For a given user utterance, you need to first detect the language, then route to the appropriate language-specific intent model. Which combination of Azure AI Language features should you use?

Accepted Answer

Language Detection and Conversational Language Understanding. Language Detection identifies the language, then CLU (Conversational Language Understanding) processes intents. Custom Text Classification is for document-level classification, not conversational intents. Translator translates text but does not detect language. Key Phrase Extraction is not needed.

Answer

Key Phrase Extraction and Conversational Language Understanding

Answer

Translator and Conversational Language Understanding

Answer

Language Detection and Custom Text Classification

Question 10

You are using Azure AI Language to analyze medical records. The built-in NER model does not recognize some medical terms. What should you do?

Accepted Answer

Train a custom NER model using Azure AI Language. Custom NER allows training a model on your specific terms. Text Analytics for Health is a specialized built-in model for healthcare but may not cover all custom terms. Custom Text Classification is for document classification. Entity Linking disambiguates to a knowledge base.

Answer

Use the Text Analytics for Health feature

Answer

Use Entity Linking

Answer

Use Custom Text Classification

Question 11

You need to translate a large batch of documents from English to multiple languages. Which Azure service should you use?

Accepted Answer

Azure AI Translator. Azure AI Translator is the correct service for text translation. Speech Translation is for real-time speech. Language Detection identifies language. CLU is for intents.

Answer

Conversational Language Understanding

Answer

Azure AI Language Detection

Answer

Azure AI Speech Translation

Question 12

Which TWO Azure AI Language features can you use to extract structured data from unstructured text?

Accepted Answer

Entity Linking. Named Entity Recognition (NER) extracts entities like people, places. Entity Linking disambiguates entities by linking to a knowledge base. Key Phrase Extraction extracts key topics but not structured data. Sentiment Analysis gives sentiment. Language Detection identifies language.

Answer

Sentiment Analysis

Answer

Language Detection

Answer

Key Phrase Extraction

Question 13

Which THREE factors should you consider when choosing between a pre-built model and a custom model in Azure AI Language?

Accepted Answer

Domain-specific vocabulary coverage. Pre-built models are faster to deploy and require no labeled data, but may not cover domain-specific terms. Custom models require labeled data and training time but offer higher accuracy for niche domains. Model size is not a typical consideration; both can be scaled. Custom models require a trained endpoint. Pre-built models are often cheaper for generic use.

Answer

Need for a trained endpoint

Answer

Model size and memory footprint

Question 14

Which TWO Azure services can be used to implement a conversational AI solution that understands user intent and responds appropriately?

Accepted Answer

Azure Bot Service. Azure Bot Service provides a framework for building bots. Conversational Language Understanding (CLU) extracts intents. Azure AI Search is for indexing/search. Translator is for translation. Speech-to-Text is for transcription.

Answer

Azure AI Speech-to-Text

Answer

Azure AI Translator

Answer

Azure AI Search

Question 15

Refer to the exhibit. You send this request to the Conversational Language Understanding API. The response includes the intent 'BookFlight' with entities 'FromCity: Seattle' and 'ToCity: Boston', but the 'Date' entity is missing. What is the most likely cause?

Accepted Answer

The model was not trained to recognize date entities. The utterance includes 'next Tuesday' but the model might not have been trained with date entities or the date entity is not defined in the schema. The API request looks correct. The missing date is not due to a different endpoint or API version.

Answer

The stringIndexType should be 'Utf16CodeUnit'

Answer

The API version does not support entity extraction

Answer

The endpoint is pointing to the wrong deployment