A Semantic Retrieval System for Case Law

Abstract

Legal reasoning, the core of legal practice in many countries, is “stare decisis” and its soundness is usually strengthened by relevant case law consulted. However, the task of relevant case law access and retrieval is tiring to legal practitioners and constitutes a serious drain on their productivity. Existing efforts at addressing this problem are conceptional, restrictive or unreliable. Specifically, existing semantic retrieval (SR) systems for case law are desirous of exceptional retrieval precision. Ontology promises to meet this desire, if introduced to the SR system. As a consequence, an ontology-based SR system for case law has been built using the systems analysis and design methodology. In particular, the component-based software engineering and the agile methodologies are employed to implement the system. Finally, the search and retrieval performance of the resultant SR system has been evaluated using the heuristics evaluation method. The retrieval system has shown to have a search and retrieval performance of about 94 % precision, 80 % recall and 84 % F-measure. Overall, the paper implements the SR system for case law with excellent precision and affirms the superiority of ontology approach over other semantic approaches to SR systems for document retrieval in the legal domain.

Natural Language Processing Technology Used in Artificial Intelligence Scene of Law for Human Behavior

“…In the same year, Ebietomere and Ekuobase applied language processing technology to the legal system for the retrieval of related cases. Compared with other algorithms, the method had obvious advantages in the literature search in the legal field [13].…”

An Estimation of Digital Learning Culture Index of Secondary Education in Nigeria

“…Equations ( 8) and ( 9) are simply the harmonic mean of teacher and student indices for the various strata with and without community consideration, respectively. The harmonic mean is particularly suitable to mitigate the effect of outliers [49,50]. Thereafter, the two-tailed type two Student's t-test probability value (p-value) was computed for zone pairs, resulting in 6 C 2 = 15 p-values computation, and between the two regions to establish statistical significance of computed DLCIs among related strata.…”