AI-102 Implement natural language processing solutions — Timed 10 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?

10 minute time limit — choose an answer to begin.

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.