IIT-KGP researchers evolve AI-aided method to automate reading of legal judgements

Researchers at IIT Kharagpur have evolved an artificial intelligence-aided method to automate reading of legal judgements.

A research team at the institute’s Department of Computer Science and Engineering has developed two deep neural models to understand the rhetorical roles of sentences in a legal case judgement, an IIT KGP statement said here.

This could be unique in India where the country uses a Common Law system that prioritises the doctrine of legal precedence over statutory law and where legal documents are often written in an unstructured way, a member of the team said.

“Taking 50 judgments from the Supreme Court of India, we have segmented these by first labelling sentences with the help of three senior law students from IIT Kharagpur’s Rajiv Gandhi School of Intellectual Property Law,” Saptarshi Ghosh, professor of the Department of Computer Science and Engineering, who is leading the research team, said.

Also read | IIT-KGP offers joint PhD programme with Auckland University

“We then performed extensive analysis of the human-assigned labels, and developed a high quality gold standard corpus to train the machine to carry out the task,” Ghosh said.

Unlike earlier attempts which required substantial human intervention, the neural methods used by professor Ghosh’s team automatically learn the features, given there is sufficient amount of data which can be used across multiple legal domains, the statement said.

This artificial intelligence-powered method would enable automated understanding of the roles of sentences in a legal case judgement, which is important as it can help in several downstream tasks such as summarisation of legal judgements, legal search, case law analysis, and other functions.

In countries such as USA, Britain, Japan, Singapore and Australia, artificial intelligence is being used to perform legal research, review documents during litigation and conduct due diligence, analyse contracts to determine whether they meet pre-determined criteria and to even predict case outcomes, it added.