Semantic Segmentation of Legal Documents via Rhetorical Roles

Abstract

Legal documents are unstructured, use legal jargon, and have considerable length, making it difficult to process automatically via conventional text processing techniques. A legal document processing system would benefit substantially if the documents could be semantically segmented into coherent units of information. This paper proposes a Rhetorical Roles (RR) system for segmenting a legal document into semantically coherent units: facts, arguments, statute, issue, precedent, ruling, and ratio. With the help of legal experts, we propose a set of 13 fine-grained rhetorical role labels and create a new corpus of legal documents annotated with the proposed RR. We develop a system for segmenting a document into rhetorical role units. In particular, we develop a multitask learning-based deep learning model with document rhetorical role label shift as an auxiliary task for segmenting a legal document. We experiment extensively with various deep learning models for predicting rhetorical roles in a document, and the proposed model shows superior performance over the existing models. Further, we apply RR for predicting the judgment of legal cases and show that the use of RR enhances the prediction compared to the transformer-based models.

Fact-based Court Judgment Prediction

“…The foundational paper "ILDC for CJPE" [10] inspired this extended study, supported by related works like "DELSumm [1], " "Identification of Rhetorical Roles of Sentences in Indian Legal Judgments [4], " and the research on semantic segmentation of legal documents [9]. These works provide a framework for our methodological design.…”

“…A rhetorical role represents the semantic meaning of a sentence in a judgement [4]. To extract the rhetorical roles of the case, we will draw upon existing techniques and tools such as "DELSumm: Incorporating Domain Knowledge for Extractive Summarization of Legal Case Documents" [1], "Identification of Rhetorical Roles of Sentences in Indian Legal Judgments" [4], "Corpus for Automatic Structuring of Legal Documents" [6], and "Semantic Segmentation of Legal Documents via Rhetorical Roles" [9].…”