Legal AI in an interdisciplinary area that cuts across the two separate domains of Law and Artificial Intelligence. The use of AI technology for legal functions has a massive potential to help free up human resources to focus on higher value-adding tasks. The major applications of AI for legal purposes can include tasks such as document automation, contract review, legal research, legal analytics and, the much disputed, litigation prediction.
India has made a head start in the area of legal AI with some promising initiatives that are already in usage, and others that are still being developed and improved by researchers. It is worth noting that of all the premier colleges in the country, Indian Institute of Technology Kharagpur has an edge in the field given that it has its own law school, called Rajiv Gandhi School of Intellectual Property Law.
- AI portal for Supreme Court: The AI-powered portal SUPACE, ie. Supreme Court Portal for Assistance in Courts Efficiency, has been launched to enhance the productivity of the legal researchers and judges in India. This integration of artificial intelligence in the judicial domain is aimed at reducing pendency and enhancing efficiency and productivity of the justice delivery. SUPACE is AI-enabled assistive tool that can augment the efficiency of the legal researchers and judges to work on cases, extract relevant information, read case files, manage teamwork and draft case documents. It is able to find facts, issues and points of law from thousands of pages of documents in a matter of seconds.
- AI system to read legal judgments: IIT Kharagpur researchers have developed an artificial intelligence-aided method to read legal judgments, which can not only tell which laws are getting violated but also in the process help minimize legal costs. This can give legal guidance to the common man to ascertain if there is merit in taking a particular situation to court. Using machine learning, they have enabled two DL models to understand the rhetorical roles of sentences in a legal case judgment.
- SC judgements available in vernacular languages: Supreme Court Vidhik Anuvaad Software (SUVAS), a machine learning tool, is being used for translating Supreme Court judgments into vernacular languages. The apex court has started translating daily orders and rulings into 9 Indian languages such as Assamese, Bengali, Hindi, Kannada, Marathi, Odiya, Tamil, Telugu and Urdu. The initiative focuses on enabling better access to justice for litigants by providing them with access to knowledge. Common people will experience reduced dependence from lawyers with the ability to independent decisions in legal matters.
- Summarisation of legal case documents: Automatic summarisation of legal case documents is an important and practical challenge. Apart from many domain-independent text summarisation algorithms that can be used for this purpose, several algorithms have been developed specifically for summarizing legal documents. However, most of the existing algorithms do not systematically incorporate domain knowledge that specifies what information should ideally be present in a legal case document summary. To address this gap, researchers from IIT KGP have propose an unsupervised summarisation algorithm DELSumm which is designed to systematically incorporate guidelines from legal experts into an optimisation setup.
- Automated extraction of catchphrases from legal documents: Legal documents can be lengthy and convoluted, making the task of understanding them strenuous and time-consuming even by legal practitioners. Thus, there arises the need for a concise representation of the legal statement which is captured through ‘catchphrases’. With the rapidly increasing number of digitized legal documents, automated extraction of such catchphrases is an essential phase of legal document indexing and legal information retrieval. Researchers at IIT KGP have modelled the catchphrases as named entities, and have trained a supervised named entity recogniser to identify them through sequence labelling. The voluminous amount of digitally available legal documents trigger the need for automated extraction of catchphrases.
Source: indiaai.gov.in
