Concept and Context in Legal Information Retrieval

There exist two broad approaches to information retrieval (IR) in the legal domain: those based on manual knowledge engineering (KE) and those based on natural language processing (NLP). The KE approach is grounded in artificial intelligence (AI) and case-based reasoning (CBR), whilst the NLP approach is associated with open domain statistical retrieval. We provide some original arguments regarding the focus on KE-based retrieval in the past and why this is not sustainable in the long term. Legal approaches to questioning (NLP), rather than arguing (CBR), are proposed as the appropriate jurisprudential and cognitive underpinning for legal IR. Recall within the context of precision is proposed as a better fit to law than the ‘total recall’ model of the past, wherein conceptual and contextual search are combined to improve retrieval performance for both parties in a dispute.