A Semi-automated Ontology Construction for Legal Question Answering

TLDR

The semantic web offers structured legal data, yet most legal information remains unstructured text, making automated natural‑language legal answer generation challenging. This paper presents a semi‑automated methodology and tool (CLOR) for generating criminal‑law ontologies that support reasoning in a legal question‑answering system by determining entailment between background information and question statements. The authors construct a criminal‑law ontology that encodes USA criminal law and procedure and legal rules, and use it within a question‑answering system to evaluate entailment between background text and question statements.

Abstract

The internet and the development of the semantic web have created the opportunity to provide structured legal data on the web. However, most legal information is in text. It is difficult to automatically determine the right natural language answer about the law to a given natural language question. One approach is to develop systems of legal ontologies and rules. Our example ontology represents semantic information about USA criminal law and procedure as well as the applicable legal rules. The purpose of the ontology is to provide reasoning support to a legal question answering tool that determines entailment between a pair of texts, one known as the background information (Bg) and the other question statement (Q), so whether Bg entails Q based on the application of the legal rules. The key contribution of this paper is the methodology and the semi-automated legal ontology generation tool, a clear and well-structured methodology that serves to develop such criminal law ontologies and rules (CLOR).