An ML engineer needs to use AWS services to identify and extract meaningful unique keywords from documents. Which solution will meet these requirements with the LEAST operational overhead?

Question

Options

• AUse the Natural Language Toolkit (NLTK) library on Amazon EC2 instances for text pre-
• BUse Amazon SageMaker and the BlazingText algorithm. Apply custom pre-processing steps for
• CStore the documents in an Amazon S3 bucket. Create AWS Lambda functions to process the
• DUse Amazon Comprehend custom entity recognition and key phrase extraction to identify and

• A
  18% (5)
• B
  7% (2)
• C
  4% (1)
• D
  71% (20)

Explanation

Amazon Comprehend is a fully managed NLP service that requires zero infrastructure setup, making it the lowest-overhead path to key phrase extraction and entity recognition - you call the API and get results.

• A is wrong because running NLTK on EC2 requires you to provision, scale, and maintain instances yourself - high operational overhead.
• B is wrong because BlazingText is a Word2Vec/text classification algorithm, not a keyword/key phrase extractor, and SageMaker still demands model training and endpoint management.
• C is wrong because chaining S3 + Lambda for NLP forces you to write and maintain the extraction logic yourself, adding both code and operational complexity.

Memory tip: When an AWS question asks for NLP tasks (sentiment, entities, key phrases, language detection) with least overhead, Comprehend is almost always the answer - it's the "no-ML-expertise-required" managed NLP service. Think of it as "Rekognition for text."

No community discussion yet for this question.