CBR-based Similar Case Retrieval from Judicial Records

Abstract

Courts require information technology that can handle the many ways that cases are handled since not all cases are handled in the same way. As a result, AI can be helpful for various sorts of court proceedings in various ways to decrease the case life cycle and cases pendency at the courts. To make legal information both understandable, actionable, and especially for providing right information at the right time, it has to be organised and given meaning. The judgement data is made available to the pub lic for awareness and guidance. The massive volume of unstructured textual material have made it challenging for AI systems to give consumers and their search queries the best recommendations. Consequently, computing the similarity between numerical data points is the most crucial component of those systems. AI may assist those seeking for information, parties to a case, and judges with structured information. A system that can retrieve similar cases will not only lessens human effort but also reduce the amount of time it would take to retrieve similar cases. The study of machine learning and natural language processing (NLP) has advanced significantly since the widespread use of the Internet. Therefore we have implemented a Siamese neural network and a LargeScale Multi-Label Text Classification having experiment with several neural classifiers to compute the judgment similarity.