Confidently extract data, topic, and document classification
Use Cases and Deployment Scope
Extracting Key-phrases and personally identifiable information from the litigation documents is the main task needed to fulfil the requirement of the clients. Using spring boot REST application, integration with Amazon Comprehend service we analyse litigation text documents files. Using java SDK, send the request to the service with a text file to extract Key-phrases and PII(personally identifiable information) and get back response with JSON format. Amazon Comprehend extract KP and PII that appears in litigation text documents.
Pros
- Amazon Comprehend identifies the language of the text and extracts Key-phrases, places, people, brands or events.
- It can build a custom set of entities or text classification models that are tailored uniquely to the organisation's need
- Amazon Comprehend's medical can be used to identify medical conditions, medications, dosages, strength and frequencies from sources like doctor's notes, clinical trial reports and patient health records. This service is very good and with well an accuracy or confidence score.
Cons
- It will be great if Amazon Comprehend provide support specifically for litigation or related text documents to extract insights from it.
- For REST API support using JAVA SDK, it will be great for developers if they provide support for testing without any credentials or account details.
- Setting up for REST API integration can be as simple as possible.
Likelihood to Recommend
Specifically, it starts processing millions of documents in minutes by leveraging the power of machine learning without having trained models from scratch. If any of the content contains personally identifiable information not only can Amazon Comprehend locate it but it will also redact or mask it. Using NLP techniques Amazon Comprehend goes well beyond keyword search or rules-based tagging to accurately classify documents. For my task or development, I cannot find any difficulties with Amazon Comprehend.
