AI-102 Implement natural language processing solutions Practice Test 10 — 15 Questions

Question 1

Based on the exhibit, which entity should you focus on improving by adding more labeled examples?

Accepted Answer

ProductName. Option A is correct because ProductName has the lowest recall (0.65) and F1 score (0.76), indicating the model is missing many instances. Adding more positive examples for ProductName would likely improve recall. Option B is wrong because OrderNumber has high recall and F1. Option C is wrong because Date has high precision and F1. Option D is wrong because all entities may not need improvement; ProductName is the weakest.

Answer

Date

Answer

OrderNumber

Answer

All entities need improvement.

Question 2

You notice a spike in errors (HTTP 429) on a specific day. What is the most likely cause?

Accepted Answer

The number of calls exceeded the rate limit for the service tier.. Option C is correct because HTTP 429 indicates rate limiting, meaning the number of calls exceeded the allowed limit for the service tier. Option A is wrong because invalid API keys would return 401, not 429. Option B is wrong because authentication failures return 401 or 403. Option D is wrong because network issues cause timeouts or 5xx errors, not 429.

Answer

Network connectivity issues.

Answer

Authentication tokens expired.

Answer

Invalid API keys were used.

Question 3

You are building a chat bot that uses Azure AI Language to process customer support tickets. The bot must extract entities like order numbers (e.g., ORD-12345) and issue categories. You need to choose the best approach for entity extraction to minimize development effort and ensure high accuracy.

Accepted Answer

Create a custom named entity recognition (NER) project in Azure AI Language that includes prebuilt components for order numbers and trains custom models for categories.. Option B is correct because the prebuilt entity components in the custom NER project can recognize common patterns like order numbers without needing to write custom regex or rules. Option A is wrong because the built-in Prebuilt Entity Extraction skill in Azure AI Search is for indexing, not for the Language service. Option C is wrong because the Conversational Language Understanding (CLU) project type is for intent classification and entity extraction, but it requires a lot of data and training. Option D is wrong because the Text Analytics for Health is for medical entities and would not work for order numbers.

Answer

Leverage the Text Analytics for Health API to extract entities from the support tickets.

Answer

Use the Prebuilt Entity Extraction skill in Azure AI Search to extract order numbers and categories from the text.

Answer

Use the Conversational Language Understanding (CLU) project type to train a model for both intent and entity extraction.

Question 4

You are developing a solution that uses Azure AI Language to analyze customer feedback. You need to determine whether the sentiment of a given sentence is positive, negative, or neutral. Which Azure AI Language feature should you use?

Accepted Answer

Sentiment Analysis. Option A is correct because Sentiment Analysis is the feature that returns sentiment labels and scores. Option B is wrong because Key Phrase Extraction identifies key phrases but not sentiment. Option C is wrong because Language Detection identifies the language. Option D is wrong because Entity Recognition identifies entities.

Answer

Entity Recognition

Answer

Language Detection

Answer

Key Phrase Extraction

Question 5

Your company uses a custom question answering knowledge base in Azure AI Language to answer employee questions about HR policies. You need to update the knowledge base with a new set of FAQ documents that contain tables and images. What is the best way to ingest the new content?

Accepted Answer

Use Microsoft Foundry Copilot Studio to automatically ingest the documents into the knowledge base.. Option C is correct because Microsoft Foundry Copilot Studio can automatically ingest structured content from documents, including tables and images, into the knowledge base. Option A is wrong because manual QnA pairs are time-consuming and error-prone. Option B is wrong because the REST API can only add QnA pairs, not directly ingest documents. Option D is wrong because Azure AI Search is for indexing, not for adding content to the knowledge base.

Answer

Use Azure AI Search to index the documents and then import the index into the knowledge base.

Answer

Manually add the new QnA pairs using the Language Studio portal.

Answer

Use the Azure AI Language REST API to add the new QnA pairs programmatically.

Question 6

You are building a multilingual chatbot using Azure AI Language. The chatbot must handle English, Spanish, and French. You need to configure the LUIS (Language Understanding) model to support multiple languages efficiently. What is the best practice?

Accepted Answer

Create a separate LUIS app for each language and use the same intents and entities structure.. Option B is correct because LUIS supports a primary language and allows using the same app for multiple languages by training separate versions. Option A is wrong because you cannot have multiple languages in a single app without separate training. Option C is wrong because the prebuilt multilingual model does not exist. Option D is wrong because LUIS does not support per-language query prediction within the same app without separate models.

Answer

Use the prebuilt multilingual LUIS model and fine-tune it with your intents.

Answer

Create a single LUIS app and add utterances in all three languages.

Answer

Create one LUIS app with language set to 'Multilingual' and add utterances in all languages.

Question 7

You are developing a solution that uses Azure AI Translator to translate documents from English to French. You need to ensure that the translated text maintains the original formatting, such as HTML tags. Which feature should you use?

Accepted Answer

Set the content type to 'text/html' in the translation request.. Option C is correct because the translator can preserve the original formatting when using the appropriate content type or using the 'textType' parameter set to 'html'. Option A is wrong because the glossary is for custom translations. Option B is wrong because the parallel corpus is for training custom models. Option D is wrong because transliteration converts between scripts, not formats.

Answer

Use the Translator glossary to preserve formatting.

Answer

Use the Translator parallel corpus to train a custom model.

Answer

Use the Transliterate method to preserve formatting.

Question 8

You are using Azure AI Language to analyze customer reviews. You need to identify specific aspects (e.g., 'price', 'service') and their associated sentiment. Which feature should you use?

Accepted Answer

Aspect-based sentiment analysis. Option D is correct because Aspect-based sentiment analysis (ABSA) identifies aspects and their sentiment. Option A is wrong because standard sentiment analysis gives overall sentiment. Option B is wrong because key phrase extraction identifies phrases but not sentiment. Option C is wrong because opinion mining is a subset of ABSA; ABSA is the correct feature name.

Answer

Opinion Mining

Answer

Sentiment Analysis

Answer

Key Phrase Extraction

Question 9

You are building a custom text classification solution in Azure AI Language. You have a dataset with 10 categories and 1000 labeled documents. You need to choose the best project type. What should you use?

Accepted Answer

Custom text classification (single or multi-label). Option A is correct because Custom text classification is designed for custom categories and can handle multiple labels per document if needed. Option B is wrong because the built-in Text Classification API only supports predefined categories. Option C is wrong because Conversational Language Understanding is for intents and entities, not text classification. Option D is wrong because Key Phrase Extraction is not a classification feature.

Answer

Conversational Language Understanding (CLU)

Answer

Key Phrase Extraction

Answer

Prebuilt Text Classification API

Question 10

You need to summarize a large document using Azure AI Language. Which feature should you use?

Accepted Answer

Document summarization. Option B is correct because Document summarization (extractive or abstractive) is designed to summarize documents. Option A is wrong because Key phrase extraction extracts phrases, not summaries. Option C is wrong because Entity recognition identifies entities. Option D is wrong because Sentiment analysis gives sentiment scores.

Answer

Key phrase extraction

Answer

Entity recognition

Answer

Sentiment analysis

Question 11

You are building a custom entity extraction solution using Azure AI Language. You have a small dataset (50 documents) with annotated entities. You need to train a model that can extract similar entities from new documents. What is the best approach?

Accepted Answer

Create a custom NER project in Azure AI Language and train it with your annotated data.. Option C is correct because Custom NER allows you to train a model with a small dataset, especially if you use active learning to improve. Option A is wrong because the prebuilt entity recognition does not cover custom entities. Option B is wrong because the built-in extractor skills in AI Search are for indexing, not for custom entity extraction. Option D is wrong because the Conversational PII entity extraction is for PII only.

Answer

Use the prebuilt entity recognition API to extract entities.

Answer

Use the Conversational PII entity extraction feature.

Answer

Use the built-in entity extraction skill in Azure AI Search.

Question 12

You are building a solution that uses Azure AI Language to analyze customer support transcripts. You need to detect personally identifiable information (PII) and also redact the detected PII from the text. Which TWO features should you use? (Select TWO.)

Accepted Answer

PII detection. Options A and C are correct. The PII detection feature identifies PII entities, and the redaction feature (available in the same API) can redact them. Option B is wrong because sentiment analysis is not for PII. Option D is wrong because key phrase extraction is not for PII. Option E is wrong because translation is not for PII detection or redaction.

Answer

Translation

Answer

Sentiment analysis

Answer

Key phrase extraction

Question 13

You are deploying a custom question answering solution in Azure AI Language. You need to ensure that the knowledge base can handle synonyms and alternative phrasings for questions. Which THREE strategies should you implement? (Select THREE.)

Accepted Answer

Add alternative question phrases to each QnA pair.. Options A, C, and D are correct. Adding alternative questions explicitly, using the synonym feature, and enabling active learning for suggestions all help handle synonyms and alternative phrasings. Option B is wrong because using a different project type is not a strategy for synonyms. Option E is wrong because increasing confidence threshold would reduce matches, not handle synonyms.

Answer

Use a custom question answering project type instead of the prebuilt one.

Answer

Increase the confidence threshold to 0.9 to reduce false positives.

Question 14

You are using Azure AI Language to analyze social media comments. You need to identify the language of each comment and then extract key phrases. Which TWO features should you use? (Select TWO.)

Accepted Answer

Language detection. Options A and D are correct. Language detection identifies the language, and key phrase extraction extracts key phrases. Option B is wrong because sentiment analysis is not for language detection. Option C is wrong because entity recognition is not for key phrases. Option E is wrong because summarization is not for key phrases.

Answer

Sentiment analysis

Answer

Summarization

Answer

Entity recognition

Question 15

Refer to the exhibit. You are configuring an Azure AI Language resource using an ARM template. The settings include PII recognition with domain set to 'phi'. What is the effect of this setting?

Accepted Answer

It will detect protected health information (PHI) such as medical record numbers.. Option C is correct. The 'phi' domain setting in PII recognition configures the service to detect protected health information (PHI) as per HIPAA. Option A is wrong because 'phi' is specifically for health information, not general PII. Option B is wrong because 'phi' does not ignore PII categories; it focuses on health-related ones. Option D is wrong because the domain setting does not affect entity recognition.

Answer

It will detect all standard PII categories plus additional health-specific entities.

Answer

It will enable the entity recognition model to detect health entities.

Answer

It will ignore PII detection and only detect health-related entities.

AI-102 Implement natural language processing solutions Practice Test 10 — 15 Questions

Exhibit

AI-102 Implement natural language processing solutions Practice Test 10 — 15 Questions

Exhibit