Legal Document Summarizer using Spacy and BART

Legal professionals face the growing challenge of managing large amounts of complex legal documents. This paper introduces a new solution that combines machine learning (ML) and natural language processing (NLP) to change the way legal documents are summarized and analyzed. Our approach leverages the ability of ML algorithms to extract important information from a variety of legal documents including contracts, court decisions, laws, and legal opinions and then uses NLP algorithms to transform that data this has been filtered into a clear and concise summary that captures the main content of original documents. This summary is not only highly accurate but also scalable to a wide range of legal documents, saving legal professionals time and resources. The authors experimented with domain-independent model for legal text summarization, called BART. Summarized documents are evaluated by registered experts against various criteria and using the ROUGE metric this shows that the text summarization is effective in legal texts with independent domain-model.