Agent-Specific Deontic Modality Detection in Legal Language

TL;DR

This paper introduces LEXDEMOD, a new annotated corpus of legal contracts for deontic modality detection, and benchmarks Transformer models on classification and span detection tasks, demonstrating generalization and practical utility.

Contribution

The paper presents LEXDEMOD, the first dataset for agent-specific deontic modality in legal language, and evaluates Transformer models for related detection tasks.

Findings

Models trained on LEXDEMOD generalize across contract types.

High recall in detecting legal red flags.

Transformer models perform well on modality classification and span detection.

Abstract

Legal documents are typically long and written in legalese, which makes it particularly difficult for laypeople to understand their rights and duties. While natural language understanding technologies can be valuable in supporting such understanding in the legal domain, the limited availability of datasets annotated for deontic modalities in the legal domain, due to the cost of hiring experts and privacy issues, is a bottleneck. To this end, we introduce, LEXDEMOD, a corpus of English contracts annotated with deontic modality expressed with respect to a contracting party or agent along with the modal triggers. We benchmark this dataset on two tasks: (i) agent-specific multi-label deontic modality classification, and (ii) agent-specific deontic modality and trigger span detection using Transformer-based (Vaswani et al., 2017) language models. Transfer learning experiments show that the linguistic diversity of modal expressions in LEXDEMOD generalizes reasonably from lease to employment and rental agreements. A small case study indicates that a model trained on LEXDEMOD can detect red flags with high recall. We believe our work offers a new research direction for deontic modality detection in the legal domain.