Struggling with Azure AI Document Intelligence model selection for scanned image text extraction, language detection, and translation? Discover why the Read model is the correct answer for this AI-102 exam scenario. Step-by-step explanation included for exam success.
Table of Contents
Question
You are planning to use Azure AI Document Intelligence to pull information from several documents.
You want to extract words from the scanned image, detect the language used in the document, and then translate key passages into the customer’s native language.
Which document model at a minimum should you use?
A. Custom neural
B. Custom classifier
C). General
D. Read
Answer
D. Read
Explanation
You would use the Read document model. This model is the primary document analysis model that allows the extraction of handwritten and printed text from PDF documents and scanned images. It will detect the language of the text which can be used for translation.
You would not use the General document model. This model has been deprecated and was used to detect check boxes and extract key-value pairs, text, tables, and structure from documents.
You would not use the Custom classifier model. This type of model is used for structured documents such as surveys and questionnaires, semi-structured documents such as invoices and purchase orders, and unstructured documents such as contracts and letters. This model provides more capabilities than necessary.
You would not use the Custom neural model. This model is used for single or multiple-file document analysis. These documents could be bank statements, loan applications, or scanned invoices. This model classifies document information into defined classes in the labeled dataset. It provides more capabilities than necessary.
Microsoft Azure AI Engineer Associate AI-102 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Engineer Associate AI-102 exam and earn Microsoft Azure AI Engineer Associate AI-102 certification.