Enhancing Legal Case Retrieval through Improved Understanding of Case Relevance
The authors propose an approach to enhance the understanding of case relevance in legal case retrieval, integrating lexical matching, semantic retrieval, and learning-to-rank techniques, along with heuristic pre-processing and post-processing methods.
ECtHR-PCR: A Dataset for Precedent Retrieval in the European Court of Human Rights
This work introduces the ECtHR-PCR dataset, a comprehensive dataset for prior case retrieval in the European Court of Human Rights, which explicitly separates facts from arguments and exhibits precedential practices.
Extracting Relevant Paragraphs from Legal Judgments Based on Queries
Automating the process of identifying paragraphs relevant to a query can streamline legal research, allowing practitioners to access crucial information efficiently.
Evaluating Ranking Changes in Live Professional Legal Search Systems: Challenges and Limitations of Common Approaches
Common ranking evaluation methods, including test collections, user surveys, and A/B testing, are suboptimal for evaluating changes to ranking algorithms in live professional legal search systems due to characteristics of the legal domain, such as high recall requirements, limited user data, and commercial constraints.
© 2024 by Linnk AI