Explainable Legal Case Matching via Graph Optimal Transport
- 13 October 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (6) , 2461-2475
Abstract
Providing human-understandable explanations for the matching predictions is still challenging for current legal case matching methods. One difficulty is that legal cases are semi-structured text documents with complicated case-case and case-law article correlations. To tackle the issue, we propose a novel graph optimal transport (GOT)-based legal case matching model that is able to provide not only the matching predictions but also plausible and faithful explanations for the prediction. The model, called GEIOT-Match, first constructs a heterogeneous graph to explicitly represent the semi-structured nature of legal cases and their associations with the law articles. Therefore, matching two legal cases amounts to identifying the rationales from the paired legal case sub-graphs in the heterogeneous graph and then aligning between them. An inverse optimal transport (IOT) model on graphs is learned to extract rationales from paired legal cases. The extracted rationales and the heterogeneous graph demonstrate the key legal characteristics of legal cases, which can be further used to conduct matching and generate explanations for the matching. Experimental results showed that GEIOT-Match outperformed state-of-the-art baselines in terms of matching prediction, rationale extraction, and natural language explanation generation.Keywords
Funding Information
- Renmin University of China
- National Natural Science Foundation of China (62376275, 62106271)
- Fundamental Research Funds for the Central Universities
- Research Funds of Renmin University of China (23XNKJ13)
- Intelligent Social Governance Interdisciplinary Platform
- Double-First Class
- Public Computing Cloud
- Renmin University of China
This publication has 45 references indexed in Scilit:
- Lawformer: A pre-trained language model for Chinese legal long documentsAI Open, 2021
- Explanation in AI and law: Past, present and futureArtificial Intelligence, 2020
- Hierarchical clustering with optimal transportStatistics & Probability Letters, 2020
- Legal requirements on explainability in machine learningArtificial Intelligence and Law, 2020
- Link Analysis for Representing and Retrieving Legal Information2013
- A history of AI and Law in 50 papers: 25 years of the international conference on AI and LawArtificial Intelligence and Law, 2012
- Improving legal information retrieval using an ontological frameworkArtificial Intelligence and Law, 2009
- Optimal Transport2009
- Knowledge Representation for the Intelligent Legal Case Retrieval2005
- Why Cannot an Effect Precede its Cause?Analysis, 1956