a fully managed, continuously trained NLP service backed by ML, used to derive meaningful data from any text in utf-8 format or semi-structured document as .doc or .pdf

Natural Language Processing a subfield of linguistics, computer science, and artificial intelligence concerned with the interactions between computers and human language. The goal is a computer capable of understanding the contents of documents, including the contextual nuances of the language within them

AWS Comprehend will scan your text looking for:

Key Phrases: combination of words that contain a noun (a word identifying people, places or things) phrase that describes something

Entities: references to the unique name of a real-world object such as people, places, and commercial items, and to precise references to measures such as dates and quantities.

Sentiments: relates to the emotional context of a block of text

Can determine what language is being used and (only in your English text documents) detect sensitive data (PII: personal identifiable information) to locate/present it or redact it directly.

Topic modelling features help you determine the themes that exist amongst a large amount of text and allows you to organise your documents into different categories.