Classification, Information Extraction and Similarity Analysis of Indian Legal Cases
Published: 2018
Author(s) Name: Aksheya Rajamani, Peeyusha Rathi, Richa Nagda, Utkarsha Nerkar and Mahesh Shirole |
Author(s) Affiliation: Dept. of Comp. Engg. and Inf. Tech., Veermata Jijabai Technological Inst., Mumbai, Maharashtra
Locked
Subscribed
Available for All
Abstract
Computer technology can be useful in facilitating legal analysis in the law system. Lakhs of case files pertaining to Indian High Courts, over the past decade, are available in digital form. The problem faced by Indian lawyers and legal personnel is that they have to go through the routine of identifying the type of document and comparing relevant or similar cases. Currently, research has been done around the world to automate the process of text classification and information extraction of legal cases. Fully automatic or semi-automatic systems that carry out semantic text analysis are far less common. However, as per our knowledge, no research has been done to automate the tedium of document review process in India. In this paper, we aim to provide a hybrid approach by combining clustering and classification techniques and develop a system to automate this process in India, using Natural Language Processing and Machine Learning.
Keywords: Classifiers, Clusters, Features, Law system, Legal cases, Regular expressions, Similarity analysis.
View PDF