nigam@COLIEE-22: Legal Case Retrieval and Entailment using Cascading of Lexical and Semantic-based models

TL;DR

This paper presents a hybrid approach combining lexical and semantic models for legal case retrieval and entailment, demonstrating that traditional BM25 outperforms neural models in this domain.

Contribution

The paper introduces a cascading method using Sentence-BERT, Sent2Vec, and BM25 for legal case tasks, highlighting the effectiveness of traditional models.

Findings

BM25 outperforms neural models in legal retrieval tasks

Hybrid models improve case entailment accuracy

Ranked 5th in COLIEE-2022 competition

Abstract

This paper describes our submission to the Competition on Legal Information Extraction/Entailment 2022 (COLIEE-2022) workshop on case law competition for tasks 1 and 2. Task 1 is a legal case retrieval task, which involves reading a new case and extracting supporting cases from the provided case law corpus to support the decision. Task 2 is the legal case entailment task, which involves the identification of a paragraph from existing cases that entails the decision in a relevant case. We employed the neural models Sentence-BERT and Sent2Vec for semantic understanding and the traditional retrieval model BM25 for exact matching in both tasks. As a result, our team ("nigam") ranked 5th among all the teams in Tasks 1 and 2. Experimental results indicate that the traditional retrieval model BM25 still outperforms neural network-based models.