Abstract
The aim of this work is to employ Tree Kernel algorithms to classify natural language in the legal domain (i.e. deontic sentences and rules). More precisely, an innovative way of extracting labelled legal data is proposed, which combines the information provided by two famous LegalXML formats: Akoma Ntoso and LegalRuleML. We then applied this method on the European General Data Protection Regulation (GDPR) to train a Tree Kernel classifier on deontic and non-deontic sentences which were reconstructed using Akoma Ntoso, and labelled using the LegalRuleML representation of the GDPR. To prove the non-triviality of the task we reported the results of a stratified baseline classifier on two classification scenarios.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Another important benefit to use AKN is to use metadata for collocating the deontic operators in the correct temporal sequence. If we have a suspension or a sunset rule or an exception we can use these important information to understand better the relationship between different parts of the discourse so as to recompose the deontic operator correctly.
- 2.
In Akoma Ntoso, atomic normative provisions can be contained in different structures (e.g. in paragraphs or list points), and may sometimes be composed of more than one sentence. We extracted these provisions from the body of the GDPR (the sentences of the preamble and conclusions are thus excluded).
- 3.
The DAPRECO knowledge base can be freely downloaded from its repository: https://github.com/dapreco/daprecokb/blob/master/gdpr/rioKB_GDPR.xml.
- 4.
The Akoma Ntoso representation of the GDPR is currently accessible from https://github.com/guerret/lu.uni.dapreco.parser/blob/master/resources/akn-act-gdpr-full.xml, where it can be freely downloaded.
- 5.
- 6.
- 7.
- 8.
These values are used within KeLP to specify the degree of sensitivity of the Tree Kernel algorithms in terms of the vertical and horizontal depth of sentences.
References
Ashley, K.D.: Artificial Intelligence and Legal Analytics: New Tools for Law Practice in the Digital Age. Cambridge University Press, Cambridge (2017)
Athan, T., Boley, H., Governatori, G., Palmirani, M., Paschke, A., Wyner, A.: Oasis legalruleml. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Law, pp. 3–12 (2013)
Chalkidis, I., Androutsopoulos, I., Michos, A.: Obligation and prohibition extraction using hierarchical RNNs. arXiv preprint arXiv:1805.03871 (2018)
Collins, M., Duffy, N.: Convolution kernels for natural language. In: Advances in Neural Information Processing Systems, pp. 625–632 (2002)
Croce, D., Moschitti, A., Basili, R.: Semantic convolution kernels over dependency trees: smoothed partial tree kernel. In: Proceedings of the 20th ACM International Conference on Information and Knowledge Management, pp. 2013–2016 (2011)
Croce, D., Moschitti, A., Basili, R.: Structured lexical similarity via convolution kernels on dependency trees. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 1034–1046 (2011)
Filice, S., Castellucci, G., Croce, D., Basili, R.: Kelp: a kernel-based learning platform for natural language processing. In: Proceedings of ACL-IJCNLP 2015 System Demonstrations, pp. 19–24 (2015)
Gao, X., Singh, M.P.: Extracting normative relationships from business contracts. In: Proceedings of the 2014 International Conference on Autonomous Agents and Multi-agent Systems, pp. 101–108 (2014)
Gomez-Perez, J.M., Denaux, R., Garcia-Silva, A.: Hybrid Natural Language Processing: An Introduction, pp. 3–6. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-44830-1_1
Kiyavitskaya, N., et al.: Automating the extraction of rights and obligations for regulatory compliance. In: Li, Q., Spaccapietra, S., Yu, E., Olivé, A. (eds.) ER 2008. LNCS, vol. 5231, pp. 154–168. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-87877-3_13
Liga, D.: Argumentative evidences classification and argument scheme detection using tree kernels. In: Proceedings of the 6th Workshop ArgMining, pp. 92–97 (2019)
Lippi, M., et al.: Claudette: an automated detector of potentially unfair clauses in online terms of service. Artif. Intell. Law, pp. 1–23 (2018)
Makinson, D., Van Der Torre, L.: Input/output logics. J. Philos. Logic 29(4), 383–408 (2000)
Moschitti, A.: Efficient convolution kernels for dependency and constituent syntactic trees. In: European Conference on Machine Learning, pp. 318–329 (2006)
Moschitti, A.: Making tree kernels practical for natural language learning. In: 11th Conference of the European Chapter of ACL (2006)
O’Neill, J., Buitelaar, P., Robin, C., O’Brien, L.: Classifying sentential modality in legal language: a use case in financial regulations, acts and directives. In: Proceedings of the 16th Edition of AI and Law, pp. 159–168 (2017)
Palmirani, M., Vitali, F.: Akoma-Ntoso for legal documents. In: Sartor, G., Palmirani, M., Francesconi, E., Biasiotti, M. (eds.) Legislative XML for the Semantic Web. Law, Governance and Technology Series, vol. 4, pp. 75–100. Springer, Dordrecht (2011). https://doi.org/10.1007/978-94-007-1887-6_6
Robaldo, L., Bartolini, C., Lenzini, G.: The DAPRECO knowledge base: representing the GDPR in LegalRuleML. In: Proceedings of the 12th Language Resources and Evaluation Conference, pp. 5688–5697 (2020)
RodrÃguez-Doncel, V., Palmirani, M., Araszkiewicz, M., Casanovas, P., Pagallo, U., Sartor, G.: Introduction: a hybrid regulatory framework and technical architecture for a human-centered and explainable AI. In: RodrÃguez-Doncel, V., Palmirani, M., Araszkiewicz, M., Casanovas, P., Pagallo, U., Sartor, G. (eds.) AICOL/XAILA 2018/2020. LNCS (LNAI), vol. 13048, pp. 1–11. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-89811-3_1
Rubino, R., Rotolo, A., Sartor, G.: An owl ontology of norms and normative judgements. In: Biagioli, C., Francesconi, E., Sartor, G. (szerk.) Proceedings of the V Legislative XML Workshop, pp. 173–187. Citeseer (2007)
Vishwanathan, S.V.N., Smola, A.J., et al.: Fast kernels for string and tree matching. Kernel Methods Comput. Biol. 15, 113–130 (2004)
Waltl, B., Muhr, J., Glaser, I., Bonczek, G., Scepankova, E., Matthes, F.: Classifying legal norms with active machine learning. In: URIX, pp. 11–20 (2017)
Wyner, A., Peters, W.: On rule extraction from regulations. In: Legal Knowledge and Information Systems, pp. 113–122. IOS Press (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liga, D., Palmirani, M. (2023). Deontic Sentence Classification Using Tree Kernel Classifiers. In: Arai, K. (eds) Intelligent Systems and Applications. IntelliSys 2022. Lecture Notes in Networks and Systems, vol 542. Springer, Cham. https://doi.org/10.1007/978-3-031-16072-1_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-16072-1_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16071-4
Online ISBN: 978-3-031-16072-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)