Semi-supervised, knowledge-integrated pattern learning approach for fact extraction from judicial text

Tremendous growth in the availability of judicial documents has demanded the rise of information extraction (IE) techniques that support the automatic extraction of relevant concepts or data from judicial texts. Among various approaches available for IE, ontology-based IE has proven to be the most appropriate for extracting domain-specific information from natural language text. Through this article, we propose a knowledge-driven, semi-supervised pattern-based learning (bootstrapping) approach to extract domain-specific facts from judicial text, starting with a small set of seed facts. In the semantic analysis of legal text, fact extraction is the next step to entity identification, which involves the identification of roles played by each entity in the judicial text. The proposed methodology learns extraction patterns for 12 classes of facts from the judicial text through the integration of the domain ontology called judicial case ontology (JCO). The experimental results were evaluated by human judges and found to be quite promising. One main feature of the proposed methodology is its portability across various domains (such as medical, banking, insurance, etc.) which in turn helps build expert systems in various sectors.