DEVELOPMENT OF A HYBRID INTELLIGENT MODEL FOR CONTRACT LITIGATION

Subject Area: Computer science

The background of the study centres on the challenges faced in contract litigation due to the complexity and volume of legal documents involved. Traditional methods of legal text analysis are often labour-intensive and prone to errors, leading to inefficiencies and potential risks in legal proceedings. To address these challenges, there is a growing interest in leveraging advanced technologies, such as natural language processing (NLP) and deep learning, to automate and improve the accuracy of legal document analysis. However, existing approaches may not fully capture the nuanced contextual information present in legal texts, leaving a gap in the literature for comprehensive solutions tailored to contract litigation. This study aims to fill this gap by proposing a novel model that integrates BM25, a Convolutional Neural Network (CNN), and a Bidirectional Long Short-Term Memory (BiLSTM). This hybrid approach combines the strengths of BM25 for efficient information retrieval, CNN for capturing local text patterns, and BiLSTM for modelling sequential dependencies, enhancing the system's ability to analyze legal documents with greater accuracy and contextual understanding. The study seeks to develop and evaluate this integrated model to provide legal professionals with a powerful tool for streamlining document review, extracting key information, and making informed legal decisions in contract litigation. Additionally, the study aims to explore the practical implications and challenges associated with implementing such technology in real-world legal settings, ultimately contributing to advancements in technology-assisted legal analysis and improving access to justice