Legal contracts have been used for millennia to conduct business transactions world-wide. Such contracts are expressed in natural language, and usually come in written form. We are interested in producing formal specifications from such legal text that can be used to formally analyze contracts, also serve as launching pad for generating smart contracts, information systems that partially automate, monitor and control the execution of legal contracts. We have been developing a method for transforming legal contract documents into specifications, adopting a semantic approach where transformation is treated as a text classification, rather than a natural language processing problem. The method consists of five steps that (a) Identify domain terms in the contract and manually disambiguate them when necessary, in consultation with stakeholders; (b) Semantically annotate text identifying obligations, powers, contracting parties, assets and situations; (c) Identify relationships among the concepts mined in (b); (d) Generate a domain model based on the terms identified in (a), as well as parameters and local variables for the contract; (e) Generate expressions that formalize the conditions of obligations and powers using terms identified in earlier steps in a contract specification language. This paper presents the method through an illustrative example, also reports on a prototype implementation of an environment that supports the method.

Contratto – A Method for Transforming Legal Contracts into Formal Specifications / Soavi, Michele; Zeni, Nicola; Mylopoulos, John; Mich, Luisa. - STAMPA. - 446:(2022), pp. 338-353. (Intervento presentato al convegno RCIS 2022 tenutosi a Barcelona, Spain nel 17th–20th May 2022) [10.1007/978-3-031-05760-1_20].

Contratto – A Method for Transforming Legal Contracts into Formal Specifications

Soavi, Michele
Primo
;
Zeni, Nicola
Secondo
;
Mylopoulos, John
Penultimo
;
Mich, Luisa
Ultimo
2022-01-01

Abstract

Legal contracts have been used for millennia to conduct business transactions world-wide. Such contracts are expressed in natural language, and usually come in written form. We are interested in producing formal specifications from such legal text that can be used to formally analyze contracts, also serve as launching pad for generating smart contracts, information systems that partially automate, monitor and control the execution of legal contracts. We have been developing a method for transforming legal contract documents into specifications, adopting a semantic approach where transformation is treated as a text classification, rather than a natural language processing problem. The method consists of five steps that (a) Identify domain terms in the contract and manually disambiguate them when necessary, in consultation with stakeholders; (b) Semantically annotate text identifying obligations, powers, contracting parties, assets and situations; (c) Identify relationships among the concepts mined in (b); (d) Generate a domain model based on the terms identified in (a), as well as parameters and local variables for the contract; (e) Generate expressions that formalize the conditions of obligations and powers using terms identified in earlier steps in a contract specification language. This paper presents the method through an illustrative example, also reports on a prototype implementation of an environment that supports the method.
2022
Research Challenges in Information Science: 16th International Conference Proceedings
Berlin
Springer
978-3-031-05759-5
Soavi, Michele; Zeni, Nicola; Mylopoulos, John; Mich, Luisa
Contratto – A Method for Transforming Legal Contracts into Formal Specifications / Soavi, Michele; Zeni, Nicola; Mylopoulos, John; Mich, Luisa. - STAMPA. - 446:(2022), pp. 338-353. (Intervento presentato al convegno RCIS 2022 tenutosi a Barcelona, Spain nel 17th–20th May 2022) [10.1007/978-3-031-05760-1_20].
File in questo prodotto:
File Dimensione Formato  
Contratto a method of transforming legal contracts into formal specifications (1).pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 2.46 MB
Formato Adobe PDF
2.46 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/344263
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact