Knowledge Representation for Legal Document Summarization

Abstract

This paper presents a novel approach for legal document summarization. Proposed approach is based on Ripple-Down Rules (RDR). It is an incremental knowledge acquisition method. RDR allows us to quickly build an extendable knowledge base using classification rules. The classification rules are written using a set of features. Summary is generated using the identified rhetorical roles in the document. Experiments demonstrate that the RDR based Legal Document summarization approach outperforms the supervised and unsupervised machine learning models.