Knowledge Representation for Legal Document Summarization

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