Anomaly Detection In Legal Documents Using Machine Learning

Legal documents have always been lengthy and it is difficult to read and understand them completely. In this project, we devise a system which is Machine Learning (ML) based tool that takes in document and highlights anomalies in the text. The document can be given as soft copies. To our knowledge, some categories of legal documents contain duplicated information that do not require our attention. However, manually extracting non-duplicate information from documents requires considerable amount of effort. Thus, we want to use machine learning algorithms to pick up unordinary sentences for us. For this purpose, we propose a set of algorithms that filters out duplicate information and returns useful information to the user. We are able to train a learner that can mark unordinary parts of a legal document for manual scrutiny. Scikit and NLTK are open source module of python which have been used to develop this tool that we’ve created. Flask modules have been used for the simple User Interface. This project contains a simplified architecture which has various algorithms and methods that have been implemented successfully.