AI-102 Implement natural language processing solutions — 100 Questions

Question 1

A company is building a chatbot using Azure Cognitive Service for Language. They need to ensure that user utterances are correctly mapped to the appropriate intent in a custom question answering project. What should they configure?

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

Accepted Answer

Add synonyms and phrase list to the custom question answering project.. Adding synonyms and phrase lists to a custom question answering project directly improves the mapping of user utterances to intents by normalizing variations in phrasing. This configuration allows the project to recognize equivalent terms (e.g., 'cost' and 'price') as the same intent, ensuring accurate intent mapping without requiring exact matches.

Answer

Add synonyms and phrase list to the LUIS application.

Answer

Add alternative question phrases to the QnA pairs in the custom question answering project.

Answer

Define entities in the custom question answering project to capture key information.

Question 2

A development team is using the Azure Cognitive Service for Language to perform sentiment analysis on social media posts. They notice that the returned sentiment scores are often neutral for posts that are clearly positive or negative. What is the most likely reason?

Accepted Answer

The posts are too short, causing the sentiment detection to default to neutral.. The Azure Cognitive Service for Language sentiment analysis API has a minimum text length requirement for reliable scoring. When input text is very short (e.g., a few words or a single sentence), the model lacks sufficient context to confidently assign a positive or negative score, so it defaults to a neutral score (often around 0.5). This is a documented behavior of the API, not a limitation of social media language support.

Answer

The service does not support sentiment analysis for social media language.

Answer

The service is not configured to detect mixed sentiment.

Answer

The posts are in a language that is not supported by the sentiment analysis API.

Question 3

Which THREE components are required to build a custom named entity recognition (NER) model in Azure Cognitive Service for Language?

Accepted Answer

A set of labeled documents for training.. A custom NER model in Azure Cognitive Service for Language requires a set of labeled documents for training. These labeled documents define the entities and their spans within text, which the model uses to learn patterns for extraction. Without labeled data, the model cannot be trained to recognize custom entities.

Answer

A QnA Maker knowledge base for entity definitions.

Answer

A LUIS application to handle entity extraction.

Question 4

A hospital uses Azure Cognitive Service for Language to extract medical entities from clinical notes. The extraction accuracy for medication names and dosages is low. The engineer needs to improve performance without adding new training data. Which solution should the engineer implement?

Accepted Answer

Use custom entity recognition with a prebuilt healthcare entity component.. The engineer can use custom entity recognition with a prebuilt healthcare entity component, which leverages the existing Text Analytics for Health model's pre-trained entities (including medication names and dosages) without requiring additional training data. This approach combines the prebuilt healthcare model's high accuracy for medical entities with custom entity recognition to fine-tune extraction for specific clinical notes, improving performance without adding new annotated data.

Answer

Add more training data with annotated entities.

Answer

Retrain the Text Analytics for Health model with additional labeled data.

Answer

Increase the confidence threshold for entity extraction.

Question 5

You are analyzing a document using Azure Cognitive Service for Language named entity recognition. The exhibit shows a partial JSON response for entity extraction. The engineer notices that 'Jane Smith' has a low confidence score of 0.45. Which action should the engineer take to improve the confidence score for similar entities?

Accepted Answer

Provide more context around the entity in the input text, such as titles or roles.. Providing more context around the entity, such as titles or roles (e.g., 'Dr. Jane Smith' or 'CEO Jane Smith'), gives the prebuilt named entity recognition (NER) model additional linguistic cues that improve its confidence in classifying the entity. Azure Cognitive Service for Language's NER uses a pre-trained model that does not support retraining with custom labels; instead, it relies on surrounding context to disambiguate entities. Adding descriptive terms helps the model leverage its training on patterns where such context correlates with higher confidence scores.

Answer

Retrain the entity recognition model with labeled examples of 'Jane Smith'.

Answer

Use a different language detection model to improve entity recognition.

Answer

Decrease the confidence threshold to 0.3 to include 'Jane Smith' as a valid entity.

Question 6

A large retail company deploys a custom text classification model using Azure Cognitive Service for Language to categorize customer support tickets into 'Billing', 'Technical', and 'General' categories. The model is trained on 10,000 labeled tickets from the past year. After deployment, the model performs well on new tickets but shows a significant drop in accuracy for tickets submitted during holiday seasons, where the volume of billing issues spikes. The engineering team suspects concept drift. They need to maintain high accuracy without manual retraining every season. Which action should the engineer take?

Accepted Answer

Enable active learning on the model and set up a human review loop for low-confidence predictions.. Active learning in Azure Cognitive Service for Language automatically identifies low-confidence predictions and sends them for human review, creating a continuous feedback loop that adapts to concept drift without manual retraining. This allows the model to improve its accuracy on seasonal billing spikes by learning from newly labeled examples, while the human review loop ensures quality control.

Answer

Add subcategories to the classification schema to better capture seasonal patterns.

Answer

Increase the number of training examples per category to 15,000 each.

Answer

Schedule monthly retraining using the original 10,000 tickets plus the new tickets.

Question 7

A company is building a chatbot using Azure Cognitive Service for Language. They need to ensure that user utterances are correctly mapped to the appropriate intent in a custom question answering project. What should they configure?

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

Accepted Answer

Enable the 'Multiple intents' setting in the Language service project.. The Azure Language Service's Conversational Language Understanding (CLU) project includes a 'Multiple intents' setting that, when enabled, allows the model to predict more than one intent per utterance. This is essential for handling compound user inputs where the user expresses multiple goals in a single sentence.

Answer

Upgrade the Language service tier from Standard to Custom.

Answer

Configure the project to use Orchestration workflow.

Answer

Set the project language to 'Multilingual' to enable entity recognition.

Answer

Define list entities for numbers and dates.

Question 8

A healthcare company is developing a solution to analyze patient feedback using Azure AI Language. The solution must extract key phrases, detect sentiment, and identify personally identifiable information (PII) such as patient names and medical record numbers from unstructured text. The company has strict compliance requirements: all text processing must occur within the United States region, and no data may leave the Azure geography. The development team has provisioned a Language resource in the East US region and has been testing the solution. During testing, the team notices that the PII detection feature is returning results, but the key phrase extraction and sentiment analysis are failing with a 403 error. The error message indicates that the resource is not allowed to access these features. The team has verified that the resource is in the S0 tier. What should the team do to resolve the issue?

Accepted Answer

Verify regional availability of the features and recreate the Language resource in a supported region if necessary.. The 403 error indicates an authorization or regional availability issue, not a tier or key problem. Key phrase extraction and sentiment analysis are available in all regions that support the Language service, but PII detection may have broader regional support. The team must verify that the East US region supports all three features; if not, they need to recreate the resource in a supported region like West US or South Central US to ensure compliance with the United States geography requirement.

Answer

Switch to the free tier to access all features.

Answer

Upgrade the Language resource to the S1 tier to enable all features.

Answer

Regenerate the API key and update the application code.

Question 9

Drag and drop the steps to deploy a custom language model using Azure AI Language into the correct order.

Accepted Answer

Step 1: Have labeled data ready, Step 2: Create the Azure AI Language resource, Step 3: Train the custom language model, Step 4: Evaluate the model performance, Step 5: Deploy the model to an endpoint. First, have labeled data ready, then create the resource, train the model, evaluate, and deploy.

Answer

Step 1: Create the Azure AI Language resource, Step 2: Have labeled data ready, Step 3: Train the custom language model, Step 4: Evaluate the model performance, Step 5: Deploy the model to an endpoint

Answer

Step 1: Have labeled data ready, Step 2: Create the Azure AI Language resource, Step 3: Evaluate the model performance, Step 4: Train the custom language model, Step 5: Deploy the model to an endpoint

Answer

Step 1: Have labeled data ready, Step 2: Create the Azure AI Language resource, Step 3: Train the custom language model, Step 4: Deploy the model to an endpoint, Step 5: Evaluate the model performance

Question 10

Match each Azure AI term to its definition.

Accepted Answer

Azure Cognitive Services: A collection of AI services and APIs that help you build intelligent applications without needing direct AI or data science skills.. Correct matches: Azure Cognitive Services provides pre-built AI APIs; Azure Machine Learning is for ML lifecycle; Azure Bot Service for building bots. Common confusion involves swapping definitions of Cognitive Services and Machine Learning.

Answer

Azure Cognitive Services: A service for building and training machine learning models.

Answer

Azure Machine Learning: A collection of pre-built AI APIs for vision, speech, language, etc.

Answer

Azure Bot Service: A service that provides pre-built AI models for natural language processing.

Question 11

You are building a multilingual support chatbot using Azure AI Language. The chatbot must understand user queries in English, Spanish, and French, and respond in the same language. The solution should minimize latency and cost. What is the recommended approach?

Accepted Answer

Use a single Azure AI Language project with multilingual support enabled.. Azure AI Language supports multilingual projects natively, allowing a single model to process queries in English, Spanish, and French without additional translation steps. This minimizes latency (no round-trip translation) and cost (no Translator API consumption), while maintaining response accuracy in the user's original language.

Answer

Use Azure AI Translator to translate all queries to English, process with an English-only project, then translate responses back.

Answer

Create separate Azure AI Language projects for each language and route queries based on detected language.

Answer

Use a single English-only project and rely on Azure AI Translator for all non-English queries.

Question 12

You are developing a conversational agent using Microsoft Copilot Studio that must handle complex multi-turn conversations. The agent needs to maintain context across multiple user inputs. Which feature should you use?

Accepted Answer

Use topics with slots to collect information across turns.. In Microsoft Copilot Studio, topics with slots are specifically designed to handle multi-turn conversations by collecting and persisting information across user inputs. Slots allow the agent to prompt for missing details and maintain context within a topic, enabling complex, stateful interactions without external dependencies.

Answer

Use actions to call external APIs for context.

Answer

Use global variables to store conversation state.

Answer

Use entities to capture user input.

Question 13

Refer to the exhibit. You submit this request to the Azure AI Language service. What is the expected response?

Accepted Answer

Both entity recognition and key phrase extraction results.. The request includes both the `entities` and `keyPhrases` tasks in the `tasks` array, which instructs the Azure AI Language service to perform both entity recognition and key phrase extraction on the same input document. The service processes each specified task independently and returns a combined response with results for both tasks, not just one.

Answer

An error because the request format is invalid.

Answer

Only key phrase extraction results.

Answer

Only entity recognition results.

Question 14

A company deploys a custom question answering project in Azure AI Language. Users report that the bot sometimes returns irrelevant answers. The knowledge base contains hundreds of QnA pairs. You need to improve answer relevance without retraining the model. What should you do?

Accepted Answer

Add alternate phrases to existing QnA pairs for common user queries.. Adding alternate phrases to existing QnA pairs directly improves the bot's ability to match user queries to the correct answer without retraining. In Azure AI Language's custom question answering, the model uses a ranker that compares the user's input against the questions and alternate phrases in the knowledge base. By providing more varied phrasings for common queries, you increase the likelihood of a high-confidence match, thereby reducing irrelevant answers.

Answer

Increase the confidence score threshold in the project settings.

Answer

Reduce the number of QnA pairs to decrease ambiguity.

Answer

Enable active learning to let the bot suggest new questions based on user queries.

Question 15

You are building a chatbot that uses Azure AI Language to extract intents and entities from user utterances. The bot must recognize custom entities like product names that are not in the default model. Which feature should you use?

Accepted Answer

Custom named entity recognition (NER) component.. Custom named entity recognition (NER) is the correct feature because it allows you to train a model to identify domain-specific entities, such as product names, that are not included in Azure AI Language's prebuilt entity catalog. Unlike prebuilt components, custom NER uses a labeled dataset to learn the exact spans of text that represent your custom entities, enabling the chatbot to extract them accurately from user utterances.

Answer

Prebuilt entity recognition component.

Answer

Key phrase extraction.

Answer

List entity in a conversational language understanding (CLU) project.

Question 16

A company uses Azure AI Language for sentiment analysis on customer feedback. They notice that the sentiment scores for mixed reviews are often neutral when they should be slightly positive. They need to improve the accuracy for these mixed reviews without labeling new data. Which approach should you recommend?

Accepted Answer

Enable opinion mining to capture aspects and opinions separately.. Enabling opinion mining allows the model to extract aspect-level sentiments, which helps to correctly interpret mixed reviews where overall sentiment is neutral but specific aspects are positive. This improves accuracy without requiring labeled data. Option A (adjusting threshold) is a heuristic that may reduce classification quality. Option C (using a different language model) is irrelevant to the problem. Option D (custom model) requires labeled data, contradicting the constraint.

Answer

Adjust the sentiment threshold to require a higher confidence for neutral.

Answer

Use a prebuilt sentiment analysis model with a different language.

Answer

Create and train a custom sentiment analysis model using labeled feedback data.

Question 17

A company uses Azure AI Language to analyze customer call transcripts. They need to identify specific entities such as product names and issue types. The prebuilt entity recognition does not cover their custom entities. Which approach should they take to extract both standard and custom entities from the transcripts?

Accepted Answer

Use a custom named entity recognition (NER) model for custom entities and call the prebuilt entity recognition API separately for standard entities.. Azure AI Language provides separate APIs for prebuilt entity recognition (covering standard entities like dates, numbers, and common types) and custom named entity recognition (NER) for domain-specific entities like product names and issue types. By using both services independently, you can extract standard entities from the prebuilt API and custom entities from a trained custom NER model, then combine the results. This approach avoids the limitations of a single model that cannot handle both predefined and custom entity types simultaneously.

Answer

Use the prebuilt entity recognition API only and map standard entities to custom categories.

Answer

Use a single conversational language understanding (CLU) project with entities defined for both standard and custom entities.

Answer

Use a custom text classification model to classify the transcript and then extract entities from the classified output.

Question 18

A company uses Azure AI Language's conversational language understanding (CLU) to build a customer support bot. They want to integrate the bot with Microsoft Teams and need to ensure that user authentication is handled by Microsoft Entra ID. However, users report that the bot sometimes fails to respond when they are not signed into Microsoft Entra ID. What is the most likely cause?

Accepted Answer

The bot's authentication settings in Azure Bot Service require Microsoft Entra ID, but the bot is not passing the token correctly.. The bot's authentication settings in Azure Bot Service require Microsoft Entra ID tokens for user authentication, but the bot is not passing the token correctly. When users are not signed into Microsoft Entra ID, the bot fails to respond because it cannot validate the user's identity via the missing or malformed token. The CLU service itself does not require tokens for prediction; the issue lies in the bot's authentication flow, not the CLU endpoint configuration.

Answer

The CLU model requires a Microsoft Entra ID token for prediction.

Answer

The CLU project endpoint is not configured to accept anonymous requests.

Answer

The bot is not registered in Microsoft Entra ID.

Question 19

Which TWO actions should you take to improve the performance of a custom named entity recognition (NER) model in Azure AI Language?

Accepted Answer

Use a balanced dataset with similar numbers of examples for each entity.. Option A is correct because a balanced dataset with similar numbers of examples for each entity prevents the model from being biased toward frequently occurring entity types, which improves per-entity precision and recall in a custom NER model. Option D is correct because adding more labeled examples with entity annotations gives the model more training signal and typically increases accuracy, especially for entity types that are underrepresented or have varied phrasing. Increasing training time (B) is not a reliable lever in Azure AI Language custom NER, since training is managed and simply running longer does not guarantee better performance and may cause overfitting. Reducing the number of entity types (C) does not inherently improve performance and may reduce the model's usefulness. Using only prebuilt entity types (E) is not applicable because the scenario concerns improving a custom NER model, and prebuilt entities cannot replace custom-labeled entity types.

Answer

Increase the training time of the model.

Answer

Reduce the number of entity types to simplify the model.

Answer

Use only prebuilt entity types to avoid training from scratch.

Question 20

Which THREE components are required to deploy a bot using Azure AI Language's conversational language understanding (CLU) and Azure Bot Service?

Accepted Answer

An Azure Bot Service bot with the CLU model as a skill.. Option A is correct because deploying a CLU-backed bot requires an Azure Bot Service bot resource that connects to the trained CLU model, typically wired in as a skill or via the CLU runtime so the bot can route utterances to the model. Option B is correct because CLU requires a conversational language understanding project containing intents and entities, and that project must have a successfully trained model before it can be consumed by the bot. Option E is correct because an Azure Bot Service bot needs a Microsoft Entra ID (Azure AD) app registration to provide the Microsoft App ID and password/secret used for authentication between the bot and the Bot Framework Service. Option C is not required because QnA Maker (now part of Azure AI Language question answering) is a separate FAQ capability and is not a prerequisite for CLU-based intent recognition. Option D is not required because a Translator resource is only needed for multilingual translation scenarios and is not part of the core CLU plus Bot Service deployment.

Answer

A QnA Maker resource for FAQs.

Answer

A Translator resource for multilingual support.