Interpretable Text Classification in Legal Contract Documents using Tsetlin Machines

Saha, Rupsa; Jyhne, Sander

doi:10.1109/istm54910.2022.00011

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Lee et al 6 , the authors proposed an automated model for extracting contract-risk to detect "poisonous" clauses in contracts, aimed at supporting contract management for construction companies. Other works [7][8][9][10][11][12] , similarly focused on the extraction or identification of specific types of contractual statements or clauses, such as obligatory or non-obligatory, ambiguous, or non-ambiguous clauses, contractual risk clauses, and specific contract elements. To the best of our knowledge, our work is the first to concentrate on a fine-grained classification of contractual obligation statements into 152 distinct classes to facilitate contracts governance.…”

Section: Related Workmentioning

confidence: 99%

A data decomposition-based hierarchical classification method for multi-label classification of contractual obligations for the purpose of their governance

Singh,

Rose Anish,

Verma

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Contract governance ensures that the agreed outcomes between customers and vendors are fulfilled. Information Technology (IT) outsourcing organizations enter thousands of contractual relationships each month leading to a high volume of business-critical contractual text that must be reviewed and deciphered for effective governance. The key to effective governance of contracts is a model that facilitates assigning ownership of the obligations to the right departments in an organization and allocating their accountability to the right stakeholders. For this, the contractual obligations need to be identified and classified so that details such as actions to be taken by departments in an organization and their ownership as per a given clause are brought out for the purpose of governance. In this paper, we present our work on automated extraction and classification of obligations present in Software Engineering (SE) contracts for the purpose of contracts governance. We propose a novel data decomposition-based hierarchical classification method for a multi-label classification of contractual obligations. We conducted experiments for a fine-grained automated classification of more than 55,000 statements from 50 large real-life SE contract documents received from a large vendor organization into 152 governance-specific classes. The results indicate that the proposed method can bring about a 7–8% improvement in accuracies when compared to state-of-the-art classification baselines such as BERT, RoBERTa, and generative models such as GPT-2.

show abstract