AI-102 Implement natural language processing solutions — 50 Questions

Question 1

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?

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

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 2

A company uses Azure AI Language Service to summarize long documents. They need to generate concise summaries that capture the main points. Which feature should they use?

Accepted Answer

Extractive Summarization. Extractive Summarization generates a concise summary by selecting the most important sentences from the document, directly producing a coherent summary. Key Phrase Extraction identifies the main topics and terms, which helps in understanding the main points even though it does not form a summary. Both features are valid for capturing main points: Extractive Summarization provides a readable summary, while Key Phrase Extraction offers a quick overview of key topics. Therefore, both options are correct for this scenario.

Answer

Entity Recognition

Answer

Sentiment Analysis

Question 3

You need to translate a large volume of documents from English to French while preserving the original formatting. Which Azure service should you use?

Accepted Answer

Azure AI Translator (Document Translation). Azure AI Translator's Document Translation feature is specifically designed to translate entire documents while preserving the original structure, layout, and formatting (e.g., tables, headers, bullet points). It supports batch processing of large volumes of documents and maintains the source file's format in the translated output, making it the correct choice for this requirement.

Answer

Azure AI Language

Answer

Custom Translator in Azure AI Translator

Answer

Azure OpenAI Service with GPT-4

Question 4

Your organization needs to analyze customer call transcripts to extract key insights, including sentiment, issues, and resolution. Which THREE Azure AI Language features should you use?

Accepted Answer

Custom named entity recognition. Custom named entity recognition (NER) allows you to train a model to extract domain-specific entities from call transcripts, such as product names, issue types, or resolution steps. This is essential for identifying the specific issues and resolutions mentioned in customer calls, which is a core requirement of the analysis.

Answer

Key phrase extraction

Answer

PII detection

Question 5

Refer to the exhibit. You are designing a Data Factory pipeline to perform sentiment analysis on a text column. The pipeline fails with a 'BadRequest' error. What is the most likely issue?

Accepted Answer

The input format is incorrect; it should be a JSON array of documents. The Cognitive Services activity in Azure Data Factory that performs sentiment analysis expects input in the form of a JSON array of documents, each containing an 'id' and 'text' field. A 'BadRequest' error typically indicates that the input format is incorrect, such as passing a single string or an improperly structured object instead of the required array. The other options are less likely because the error is specifically related to the request payload format.

Answer

The output variable 'sentimentResult' is not defined

Answer

The activity type should be 'AzureFunction'

Answer

The linked service name is misspelled

Question 6

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. Aspect-based sentiment analysis (C) is the correct feature because it specifically identifies individual aspects (e.g., 'price', 'service') within text and determines the sentiment associated with each aspect. In Azure AI Language, this is implemented via the 'Sentiment Analysis' API with opinion mining enabled, which extracts targets (aspects) and their corresponding assessments (opinions) to provide granular sentiment scores per aspect.

Answer

Opinion Mining

Answer

Sentiment Analysis

Answer

Key Phrase Extraction

Question 7

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.. Adding alternative question phrases to each QnA pair directly expands the surface area of possible user queries that will match a given answer. This is a core feature of custom question answering in Azure AI Language, allowing you to predefine synonyms and rephrasings for each QnA pair without relying on external logic.

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 8

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 A. Active learning in Azure AI Language custom NER automatically identifies the most informative unlabeled documents and suggests labels for them, which directly targets the underperforming entity types ('Statute' and 'Case Citation') without requiring manual labeling of the entire dataset. This reduces labeling effort significantly while improving model accuracy by focusing on ambiguous or high-uncertainty examples.

Answer

Option D

Answer

Option B

Answer

Option C

Question 9

A legal compliance team needs to automatically redact personally identifiable information (PII) from legal documents before sharing them with external auditors. The documents are stored in Azure Blob Storage. The solution must use Azure AI Language to detect PII and then redact the identified entities. The redaction must be performed on the original documents, and the redacted versions must be saved to a separate container. You need to design a serverless solution with minimal latency. What should you do?

Accepted Answer

Create an Azure Function triggered by Blob Storage events to detect PII, redact, and save to a separate container.. Azure Functions can be triggered by Blob Storage events, process each document using the PII detection API, redact the entities, and save the redacted version to a separate container. This is serverless and efficient, providing minimal latency. Option C is correct. Option A (Azure Data Factory) is designed for data movement and orchestration, not for real-time event-driven processing; it would introduce unnecessary latency. Option B (Azure Batch Service) is intended for large-scale batch processing, not for processing individual documents as they are added. Option D (Azure Logic Apps) can be used, but it typically has higher latency due to its connector-based architecture and multi-tenant execution environment, making it less suitable for minimal latency requirements.

Answer

Use Azure Data Factory to copy documents to a processing location and call an Azure Function.

Answer

Use Azure Batch Service to process documents in parallel and redact PII.

Answer

Use Azure Logic Apps with a Blob trigger to call the PII detection API and write redacted documents.

Question 10

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?

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 11

A development team is using Azure Cognitive Service for Language to extract key phrases from customer reviews. They notice that some reviews are not being processed, and the API returns a 400 error code. What is the most likely cause?

Accepted Answer

One of the reviews exceeds the maximum character limit for a single document.. The Azure Cognitive Service for Language key phrase extraction API enforces a maximum document size of 5,120 characters per document. When a single review exceeds this limit, the API returns a 400 Bad Request error because the request payload violates the service's input constraints. This is the most common cause of 400 errors in batch text analysis operations.

Answer

The reviews contain characters that are not valid UTF-8.

Answer

The request contains more than 5 documents.

Answer

The reviews are written in a language not supported by the service.

Question 12

A company is using Azure Cognitive Service for Language to analyze customer support transcripts. They want to identify custom categories (e.g., 'billing', 'technical support') using a custom text classification model. After training and deploying the model, they receive many false positives for the 'billing' category. What is the best first step to improve model accuracy?

Accepted Answer

Review the training data for the 'billing' category and correct any mislabeled examples.. False positives for a specific category like 'billing' most often stem from mislabeled or ambiguous training examples in that category. By reviewing and correcting the training data for 'billing', you directly address the root cause of the model's confusion, which is the most effective first step in custom text classification model improvement.

Answer

Add more training data to all categories to improve overall model performance.

Answer

Use a different Azure AI service, such as key phrase extraction, to identify billing-related content.

Answer

Increase the confidence threshold for the 'billing' category to reduce false positives.

Question 13

A company wants to use Azure AI Translator to translate customer emails from English to French. They need to ensure that the translation preserves the tone and formality of the original text. What should they configure in the request?

Accepted Answer

Set the 'formality' parameter to the desired level (e.g., 'formal' or 'informal').. Azure AI Translator provides a 'formality' parameter that allows you to specify the desired level of formality (e.g., 'formal' or 'informal') in the translated text. This parameter directly controls the tone and register of the output, ensuring that the translation preserves the original email's tone and formality, which is critical for customer communications.

Answer

Set the 'category' parameter to 'general' to use a standard translation model.

Answer

Set the 'scope' parameter to 'document' to ensure context-aware translation.

Answer

Set the 'language' parameter to 'fr' and the 'from' parameter to 'en'.

Question 14

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 15

Which TWO actions should you take to optimize a custom text classification model in Azure Cognitive Service for Language?

Accepted Answer

Ensure that training examples for different labels do not have overlapping content.. Overlapping content between labels (e.g., the same text appearing in both 'positive' and 'negative' training examples) confuses the custom text classification model, leading to poor decision boundaries. Azure Cognitive Service for Language uses a multi-class or multi-label classifier that learns distinct patterns for each label; overlapping content introduces ambiguity, reducing precision and recall. Ensuring distinct, non-overlapping training examples per label helps the model learn clear, separable features.

Answer

Oversample the minority classes to balance the dataset.

Answer

Remove all stop words from the training data.

Answer

Remove examples with neutral sentiment to focus on positive and negative classes.

Question 16

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 17

A company is building a chatbot using Azure Bot Service and Language Understanding (LUIS). The chatbot needs to handle user intents for booking flights and checking flight status. After testing, the chatbot frequently fails to distinguish between the two intents when users mention flight numbers. Which action should the engineer take to improve intent recognition?

Accepted Answer

Add more utterances that include flight numbers to the training data for both intents.. Adding more utterances that include flight numbers to both intents provides LUIS with more varied examples of how flight numbers appear in natural language, enabling the model to learn distinguishing patterns. Without sufficient training data containing flight numbers, LUIS cannot reliably differentiate between 'BookFlight' and 'CheckFlightStatus' when users mention flight numbers, as the entity alone does not determine intent.

Answer

Increase the number of intents to split the flight-related queries further.

Answer

Reduce the confidence score threshold for intent detection.

Answer

Use the prebuilt domain for flight booking to improve accuracy.

Question 18

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 19

A developer is using Azure Cognitive Service for Language to perform sentiment analysis on customer reviews. The service returns sentiment labels (positive, negative, neutral) and confidence scores. For a particular review, the service returns 'positive' with a confidence score of 0.55. The developer wants to ensure that only high-confidence results are used. What should the developer do?

Accepted Answer

Configure a minimum confidence threshold of 0.75 in the application logic.. The developer must implement a confidence threshold in the application logic to filter out low-confidence results. The Azure Cognitive Service for Language returns confidence scores between 0 and 1 for each sentiment label, and the developer can set a minimum threshold (e.g., 0.75) to ensure only high-confidence predictions are used. This approach does not require retraining the model or modifying the input text, as the threshold is applied post-inference in the client code.

Answer

Use the Text Analytics for Health API instead.

Answer

Retrain the sentiment analysis model with additional labeled data.

Answer

Adjust the input text by removing ambiguous phrases.

Question 20

Which THREE actions should an engineer take when deploying a custom question answering project in Azure Cognitive Service for Language?

Accepted Answer

Set up a multi-turn extraction policy for follow-up questions.. Multi-turn extraction is a core feature of custom question answering that allows the system to handle follow-up questions by maintaining context across turns. This is essential for conversational flows where a user's subsequent query depends on the previous answer, and it is configured via the project settings in Language Studio.

Answer

Integrate LUIS for intent detection.

Answer

Configure a single-turn extraction policy.