PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #211
You work for a hotel and have a dataset that contains customers' written comments scanned from paper-based customer feedback forms, which are stored as PDF files. Every form has the same layout. You n
The correct answer is C. Uptrain a Document AI custom extractor to parse the text in the comments section of each PDF. To quickly predict overall satisfaction from customer comments in scanned, consistent-layout PDF forms, a Document AI custom extractor should be trained to specifically parse the text from the comments section.
Question
Options
- AUse the Vision API to parse the text from each PDF file. Use the Natural Language API
- BUse the Vision API to parse the text from each PDF file. Use the Natural Language API
- CUptrain a Document AI custom extractor to parse the text in the comments section of each PDF
- DUptrain a Document AI custom extractor to parse the text in the comments section of each PDF
How the community answered
(34 responses)- A9% (3)
- B3% (1)
- C76% (26)
- D12% (4)
Why each option
To quickly predict overall satisfaction from customer comments in scanned, consistent-layout PDF forms, a Document AI custom extractor should be trained to specifically parse the text from the comments section.
While the Vision API can perform Optical Character Recognition (OCR) on PDFs, it is a more general-purpose tool and less optimized for structured document understanding and field extraction compared to Document AI, especially when forms have a consistent layout.
While the Vision API can perform Optical Character Recognition (OCR) on PDFs, it is a more general-purpose tool and less optimized for structured document understanding and field extraction compared to Document AI, especially when forms have a consistent layout.
A Document AI custom extractor is ideal for this scenario because it can be trained to precisely identify and extract text from specific fields, like a comments section, within structured documents like feedback forms with consistent layouts. Once the relevant text is extracted, it can then be fed into a natural language model for sentiment analysis to predict an overall satisfaction score.
Option D is textually identical to option C and is correct for the same reasons.
Concept tested: Document AI for structured document extraction
Source: https://cloud.google.com/document-ai/docs/extract-data
Topics
Community Discussion
No community discussion yet for this question.