Many recent and highly effective retrieval models for long queries use query reformulation methods that jointly optimize term weights and term selection. These methods learn using word context and global context but typically fail to capture query context. In this paper, we present a novel term ranking algorithm, PhRank, that extends work on Markov chain frameworks for query expansion to select compact and focused terms from within a query itself. This focuses queries so that one to five terms in an unweighted model achieve better retrieval effectiveness than weighted term selection models that use up to 30 terms. PhRank terms are also typically compact and contain 1-2 words compared to competing models that use query subsets up to 7 words long. PhRank captures query context with an affinity graph constructed using word co-occurrence in pseudo-relevant documents. A random walk of the graph is used for term ranking in combination with discrimination weights. Empirical evaluation using newswire and web collections demonstrates that performance of reformulated queries is significantly improved for long queries and at least as good for short, keyword queries compared to highly competitive information retrieval (IR) models.

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.