Statute-enhanced lexical retrieval of court cases for COLIEE 2022

TL;DR

This paper explores enhancing court case retrieval by integrating statute information and passage-level ranking, leading to improved recall in a legal retrieval task.

Contribution

It introduces a method that incorporates statute data into passage-level retrieval, outperforming traditional document-level approaches in legal case retrieval.

Findings

Passage-level retrieval with rank fusion outperforms document-level retrieval.

Adding statute information improves retrieval results.

High recall achieved, but precision remains low.

Abstract

We discuss our experiments for COLIEE Task 1, a court case retrieval competition using cases from the Federal Court of Canada. During experiments on the training data we observe that passage level retrieval with rank fusion outperforms document level retrieval. By explicitly adding extracted statute information to the queries and documents we can further improve the results. We submit two passage level runs to the competition, which achieve high recall but low precision.