English

Annotation and Classification of Relevant Clauses in Terms-and-Conditions Contracts

Computation and Language 2024-05-28 v2

Abstract

In this paper, we propose a new annotation scheme to classify different types of clauses in Terms-and-Conditions contracts with the ultimate goal of supporting legal experts to quickly identify and assess problematic issues in this type of legal documents. To this end, we built a small corpus of Terms-and-Conditions contracts and finalized an annotation scheme of 14 categories, eventually reaching an inter-annotator agreement of 0.92. Then, for 11 of them, we experimented with binary classification tasks using few-shot prompting with a multilingual T5 and two fine-tuned versions of two BERT-based LLMs for Italian. Our experiments showed the feasibility of automatic classification of our categories by reaching accuracies ranging from .79 to .95 on validation tasks.

Keywords

Cite

@article{arxiv.2402.14457,
  title  = {Annotation and Classification of Relevant Clauses in Terms-and-Conditions Contracts},
  author = {Pietro Giovanni Bizzaro and Elena Della Valentina and Maurizio Napolitano and Nadia Mana and Massimo Zancanaro},
  journal= {arXiv preprint arXiv:2402.14457},
  year   = {2024}
}

Comments

LREC-COLING 2024. https://aclanthology.org/2024.lrec-main.108