Semantic Annotation of Legal Contracts with ContrattoA

The aim of the research is to semi-automate the process of generating formal specifications 9 from legal contracts in natural language text form. Towards this end, the paper presents a tool, 10 named ContrattoA, that semi-automatically conducts semantic annotation of legal contract text us- 11 ing an ontology for legal contracts. ContrattoA was developed through two iterations where lexical 12 patterns were defined for legal concepts and their effectiveness was evaluated with experiments. 13 The first iteration was based on a handful of sample contracts and resulted in defining lexical pat- 14 terns for recognizing concepts in the ontology; these were evaluated with an empirical study where 15 one group of subjects was asked to annotate legal text manually, while a second group edited the 16 annotations generated by ContrattoA. The second iteration focused on the lexical patterns for the 17 core contract concepts of obligation and power where results of the first iteration were mixed. On 18 the basis of an extended set of sample contracts, new lexical patterns were derived and those were 19 shown to improve substantially the performance of ContrattoA, nearing in quality the performance 20 of experts. The experiments suggest that good quality annotations can be generated for a broad 21 range of contracts with minor refinements to the lexical patterns.