Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/22605
Title: | Integrating natural language and formal analysis for legal documents |
Authors: | Azzopardi, Shaun Gatt, Albert Pace, Gordon J. |
Keywords: | Natural language processing (Computer science) Corpora (Linguistics) Linguistic analysis (Linguistics) Reference (Linguistics) Word (Linguistics) |
Issue Date: | 2016 |
Publisher: | Slovenian Language Technologies Society |
Citation: | Azzopardi, S., Gatt, A., & Pace, G. J. (2016). Integrating natural language and formal analysis for legal documents. 10th Conference on Language Technologies and Digital Humanities, Ljubljana. 1-4. |
Abstract: | Although much research has gone into natural language legal document analysis, practical solutions to support legal document drafting and reasoning are still limited in number and functionality. However given the textual basis of law there is much potential for NLP techniques to aid in the context of drafting legal documents, in particular contracts. Furthermore, there is a body of work focusing on the formal semantics of norms and legal notions which has direct applications in analysis of such documents. In this paper we present our attempt to use several off-the-shelf NLP techniques to provide a more intelligent contract editing tool to lawyers. We exploit these techniques to extract information from contract clauses to allow intelligent browsing of the contract. We use this surface analysis to bridge the gap between the English text of a contract to its formal representation, which is then amenable to automated deduction, specifically it allows us to identify conflicts in the contract. |
URI: | https://www.um.edu.mt/library/oar//handle/123456789/22605 |
Appears in Collections: | Scholarly Works - InsLin |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
ltdh2016-contracts.pdf | 203.19 kB | Adobe PDF | View/Open |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.