Microsoft Azure AI Fundamentals (AI-900) Practice Exam

Which service can automatically extract text, key/value pairs, and table data from scanned documents?

1. Form Recognizer

2. Text Analytics

3. Computer Vision

4. Content Moderator

The correct answer is: Form Recognizer

The Form Recognizer service is specifically designed to extract structured information from documents, such as text, key/value pairs, and table data. This service utilizes advanced machine learning models to identify and extract relevant information from various types of documents, including scanned images and PDFs. By training on sample documents, Form Recognizer can adapt to different formats and layouts, making it highly effective for automating the data extraction process from forms and documents. In contrast, Text Analytics focuses on processing and analyzing textual data to derive insights such as sentiment analysis, key phrase extraction, and language detection, rather than extracting structured data from documents. Computer Vision is another robust service that analyzes images to identify objects, people, or actions in visual content, but it does not specialize in document text extraction. Content Moderator, on the other hand, is aimed at detecting potentially offensive content in text and images, rather than processing or extracting structured information from documents. Thus, Form Recognizer stands out as the correct choice for this particular use case.