IITP@COLIEE 2019: Legal Information Retrieval using BM25 and BERT

TL;DR

This paper describes the use of BM25 and BERT models for legal information retrieval in the COLIEE-2019 competition, demonstrating effective approaches across multiple sub-tasks in the judicial domain.

Contribution

It presents a combination of IR and deep learning techniques, including BM25 and BERT, applied to legal information retrieval tasks in a competitive setting.

Findings

Encouraging results across all four sub-tasks

Effective application of BM25 and BERT in legal IR

Improved automation tools for the judicial system

Abstract

Natural Language Processing (NLP) and Information Retrieval (IR) in the judicial domain is an essential task. With the advent of availability domain-specific data in electronic form and aid of different Artificial intelligence (AI) technologies, automated language processing becomes more comfortable, and hence it becomes feasible for researchers and developers to provide various automated tools to the legal community to reduce human burden. The Competition on Legal Information Extraction/Entailment (COLIEE-2019) run in association with the International Conference on Artificial Intelligence and Law (ICAIL)-2019 has come up with few challenging tasks. The shared defined four sub-tasks (i.e. Task1, Task2, Task3 and Task4), which will be able to provide few automated systems to the judicial system. The paper presents our working note on the experiments carried out as a part of our participation in all the sub-tasks defined in this shared task. We make use of different Information Retrieval(IR) and deep learning based approaches to tackle these problems. We obtain encouraging results in all these four sub-tasks.