AI-102 Question 368
Select 3You are tasked with creating a cognitive search solution in Azure and need to define a skillset for enriching your data. The dataset contains unstructured PDF documents, and you want to extract text, key phrases, and image content from these files. Which of the following components should be included in your skillset?
- A
A Text Extraction skill
- B
A Key Phrase Extraction skill
- C
An Image Analysis skill
- D
A Sentiment Analysis skill
- E
A Language Detection skill
Show answer and explanation
Correct answers: A, B, C
Explanation
In this scenario, you are working with unstructured PDF documents and need to enrich the data by extracting text, identifying key phrases, and analyzing embedded images. A Text Extraction skill is used to extract the text, a Key Phrase Extraction skill identifies relevant phrases, and an Image Analysis skill processes the images. Skills unrelated to the stated requirements, such as Sentiment Analysis and Language Detection, are not necessary.
- A. Correct.
A Text Extraction skill is necessary to extract text content from the unstructured PDF documents.
- B. Correct.
A Key Phrase Extraction skill is used to identify key phrases within the text extracted from the PDFs, which is required in this scenario.
- C. Correct.
An Image Analysis skill is necessary to extract content or metadata from any images embedded within the PDF documents.
- D. Incorrect.
A Sentiment Analysis skill is not required in this scenario as it is used to detect sentiment in textual data, which is not a stated requirement.
- E. Incorrect.
A Language Detection skill is not needed here because there is no requirement to identify the language of the text.