In countries following the Common Law system (e.g., India, UK, Canada, Australia, and many others), there are two primary sources of law
While working on a new case a legal practitioner often relies on these statutes and precedents to understand how the Court has discussed, argued and behaved in similar scenarios. This task is aimed at creating retrieval systems capable of addressing this problem
Given a query (short description of a legal situation), identify relevant statutes and prior-cases. As both statute retrieval and precedent retrieval pose different types of challenges we subdivide this task into two subtasks described below. Participants can submit runs for either or both subtasks. The queries for both sets of task will be the same, but the document collection will be different.
The dataset consists of ~3000 judgements delivered by the Supreme Court of India. For each query, the task is to retrieve the most similar / relevant case documents with respect to the situation in the given query.
We have identified a set of 197 statutes (Sections of Acts) from Indian law, that are relevant to some of the queries. We provide the title and description of these statutes. For each query, the task is to identify the most relevant statutes (from among the 197 statutes).
This is a continuation of AILA 2019 track. Last years dataset (both train and test) will be provided to the participants as this year's training data. This years test data will consist of an additional queries, while retaining the same document collection. More details can be found on the dataset page.
Note: Both the tasks can be modelled either as an unsupervised retrieval task (where you search for relevant statues/precedent) or as a supervised classification task (e.g., trying to predict for each statute /precedent whether it is relevant)