Artificial-Intelligence-for-Legal-Assistance
This was built as a part of the course Information Retrieval CS6370 at IIT Hyderabad
Given 3k legal documents of cases judged by Supreme Court of India— for each query, the task is to retrieve the top-k relevant case documents with respect to the situation in the given query. Built an IR system using tf-idf, k-means clustering, word2vec, distilBERT and other approaches with an overall precision@k of 0.12 and recall@k of 0.32.