Extractive Summarization of Indian Legal Documents

Abstract

AbstractA legal document is generally very long and possess hierarchical structure which makes it very difficult to get a quick understanding of these documents. Legal practitioners generally engage legal experts for making summaries of lengthy documents which is a very costly and time-consuming process. Recently, automatic summarization systems have been proposed to deal with this problem, which has the potential to be much more efficient at simplifying complicated legal documents. In this work, web scrapping is used for extraction of legal documents. Then, a comparative analysis is done on these documents using various extractive summarization approaches. From the experimental results, it has been found that the graph-based approaches performed well in general. Another important finding is that, in addition to the frequency of words, other information such as context information, lexical information is also equally important for summarization and can improve the performance of summarization systems.KeywordsExtractive summarizationLegal document summarizationComparative analysis