Q: 9
A company manually reviews all submitted resumes in PDF format. As the company grows, the
company expects the volume of resumes to exceed the company's review capacity. The company
needs an automated system to convert the PDF resumes into plain text format for additional
processing.
Which AWS service meets this requirement?
Options
Discussion
A . B is a trap here since Personalize is for recommendations, not text extraction. Lex and Transcribe are speech-focused. Textract is literally made for extracting text from PDFs, so makes sense for this scenario.
Its A, official exam guide and practice test both mention Textract for PDF text extraction.
Probably A, but if you look at the official AWS practice test and exam guide, Textract is the go-to for extracting text from PDFs. Transcribe is just for audio so I don't think that's it. If someone saw this worded weird on their exam let me know.
A is wrong, D. Amazon Transcribe can handle text extraction, so it should work for PDFs just as well. Textract may be a trap since it's more about forms or images but not always needed for plain text conversion. Correct me if I'm missing something.
A , Amazon Textract is built for extracting text from PDFs, including both scanned images and digital files. D (Transcribe) is a common trap here but that only works for audio, not documents. Personalize and Lex are unrelated to resume conversion. Pretty sure A fits best for the exam's wording.
Makes sense to pick A here, since Textract is built for pulling text from both scanned and native PDFs. The others aren't really geared for document processing at all. Pretty sure that's what AWS expects, but open if someone sees it differently.
B tbh is a trap, that's for personalization not text extraction. A is the only one that handles PDFs directly.
I don't think it's D here. Transcribe only works for audio files, not PDFs, so picking it would be a mistake. Amazon Textract (A) is made to handle text extraction from documents like resumes in PDF format. So pretty confident it's A, unless I'm missing some detail in the question wording.
Its D. Feels like a trick since Transcribe handles audio to text but not PDFs, but sometimes exam wording trips you up.
B , because if the question was about recommendations or matching, Personalize would fit, but this feels like a text extraction task so maybe it's still actually A? Not 100% sure.
Be respectful. No spam.
