Amazon Comprehend Documentation
Amazon Comprehend is a natural language processing (NLP) service that enables the use of machine learning to discover insights from text.
Sentiment Analysis
The Sentiment Analysis API is designed to return an overall sentiment score of a text and the sentiment associated with a particular entity in a text input (Positive, Negative, Neutral, or Mixed).
Syntax Analysis
The Amazon Comprehend Syntax API enables customers to analyze text using tokenization and Parts of Speech (PoS), and identify word boundaries and labels like nouns and adjectives within the text.
Entity Recognition
The Entity Recognition API is designed to return named entities ("People," "Places," "Locations," etc.) that are categorized based on the provided text.
Custom Entity Recognition
Custom Entities allows you to customize Amazon Comprehend to identify terms that are specific to your domain. Using AutoML, Comprehend is designed to learn from a small private index of examples (for example, a list of policy numbers and text in which they are used), and then train a private, custom model to recognize these terms in any other block of text.
Language Detection
The Language Detection API is designed to identify text written in over 100 languages and return the dominant language with a confidence score to support that a language is dominant.
Custom Classification
The Custom Classification API enables you to build custom text classification models using your business-specific labels. It is designed so you can provide examples of text for each of the labels you want to use, and Comprehend trains on those to create your custom model.
Topic Modeling
Topic Modeling is designed to identify relevant terms or topics from a collection of documents. It is also enabled to help identify the most common topics in the collection and organize them in groups and then map which documents belong to which topic.
PII Identification and redaction
Amazon Comprehend ML capabilities are designed to help detect and redact personally identifiable information (PII).
Toxicity detection
Amazon Comprehend toxicity detection is designed to provide a NLP (natural language processing)-based solution for toxic content detection in text-based documents.
Prompt safety classification
Amazon Comprehend provides a pre-trained binary classifier designed to classify the input prompt as harmful or not.
Keyphrase extraction
The keyphrase extraction API is designed to return the key phrases or talking points and a confidence score to support that this is a key phrase.
Events detection
Amazon Comprehend events enables you to extract the event structure from a document.
Additional Information
For additional information about service controls, security features and functionalities, including, as applicable, information about storing, retrieving, modifying, restricting, and deleting data, please see https://docs.aws.amazon.com/index.html. This additional information does not form part of the Documentation for purposes of the AWS Customer Agreement available at http://aws.amazon.com/agreement, or other agreement between you and AWS governing your use of AWS’s services.