Automated Techniques on Indian Legal documents: A Review

The usage of legal documents has increased tremendously due to its easy availability in electronic format. This has given a wide range of exposure to the research areas. An automated mechanism that processes legal data can lead the law to a new dimension. Different deep learning and artificial intelligence techniques have been applied to the Indian legal document. In this paper, we review about the different techniques like Recurrent Network Networks (RNN), Bidirectional Encoder Representations from Transformers (BERT), Robustly Optimized BERT Pre-training Approach(RoBERTa), Best Matching (BM25) algorithm, Support Vector Machine (SVM), Long Short-Term Memory(LSTM) that have been applied on the Indian legal document for summarising, prediction, text classification and multi-class text classification. This review will give a conclusion that the deep learning techniques will give a better performance than the others.