Spectre@AILA-FIRE2020 - Supervised Rhetorical Role Labeling for Legal Judgments using Transformers.

This paper presents the methodologies implemented while performing multi-class text classification for rhetorical role labeling of legal judgments for task 2 of the track ‘Artificial Intelligence for Legal Assistance’ proposed by the Forum of Information Retrieval Evaluation in 2020. A transformer-based language model (RoBERTa) pretrained over an extensive English language corpus and fine-tuned on legal judgments from the Supreme Court is presented along with its evaluation on standard classification metrics, precision, recall, and F-score.