Improving Similar Case Retrieval Ranking Performance By Revisiting RankSVM

TL;DR

This paper explores improving legal case retrieval ranking by replacing traditional classifiers with RankSVM, demonstrating enhanced performance and reduced overfitting on benchmark datasets.

Contribution

It introduces the use of RankSVM as a pairwise learning-to-rank method to improve legal case retrieval performance over existing classifiers.

Findings

RankSVM improves retrieval accuracy on LeCaRD datasets

It helps mitigate overfitting caused by class imbalance

The approach outperforms original classifiers in ranking tasks

Abstract

Given the rapid development of Legal AI, a lot of attention has been paid to one of the most important legal AI tasks--similar case retrieval, especially with language models to use. In our paper, however, we try to improve the ranking performance of current models from the perspective of learning to rank instead of language models. Specifically, we conduct experiments using a pairwise method--RankSVM as the classifier to substitute a fully connected layer, combined with commonly used language models on similar case retrieval datasets LeCaRDv1 and LeCaRDv2. We finally come to the conclusion that RankSVM could generally help improve the retrieval performance on the LeCaRDv1 and LeCaRDv2 datasets compared with original classifiers by optimizing the precise ranking. It could also help mitigate overfitting owing to class imbalance. Our code is available in https://github.com/liuyuqi123study/RankSVM_for_SLR