Legal data extraction and possible applications

Abstract

The functioning of the modern society provokes creation of significant number of documents, most of them in text form. Many of them are legally relevant and complex in nature, which makes their understanding difficult. They are written in nature language for people, which is hard for computer processing and hence hard for further analysis. Documents represent an abundance of data in unstructured form. They can be handled using NLP methodology. Different models, trained for specific use cases are used, depending on a type of legal document. Automation of number of processes can save time and speed up work on document processing. This, of course, does not rule out the need for highly qualified lawyers. The goal is to ease their work in terms of processing large amount of documents. Increased productivity should be beneficial for both natural and legal persons when working with textual and legal issues.