ABSTRACT
In this paper we use statistical machine learning to classify statutory texts in terms of highly specific functional categories. We focus on regulatory provisions from multiple US state jurisdictions, all dealing with the same general topic of public health system emergency preparedness and response. In prior work we have established that one can improve classification performance on one jurisdiction's statutory texts using texts from another jurisdiction. Here we describe a framework facilitating transfer of predictive models for classification of statutory texts among multiple state jurisdictions. Our results show that the classification performance improves as we employ an increasing number of models trained on data coming from different states.
- I. Batal, C. Hong, and M. Hauskrecht. An efficient probabilistic framework for multi-dimensional classification. In CIKM, pages 2417--2422, 2013. Google ScholarDigital Library
- C. Biagioli, E. Francesconi, A. Passerini, S. Montemagni, and C. Soria. Automatic semantics extraction in law documents. In ICAIL '05, pages 133--140. ACM, 2005. Google ScholarDigital Library
- G. Boella, L. D. Caro, L. Lesmo, D. Rispoli, and L. Robaldo. Multi-label classification of legislative text into eurovoc. In B. Schäfer, editor, JURIX 2012, pages 21--30. IOS Press, 2012.Google Scholar
- N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer. Smote: Synthetic minority over-sampling technique. J. Artif. Int. Res., 16: 321--357, 2002. Google ScholarDigital Library
- V. Daudaravicius. Automatic multilingual annotation of eu legislation with eurovoc descriptors. In EEOP2012 Workshop Proceedings, 2012.Google Scholar
- E. de Maat, K. Krabben, and R. Winkels. Machine learning versus knowledge based classification of legal texts. In R. Winkels, editor, JURIX 2010, pages 87--96. IOS Press, 2010. Google ScholarDigital Library
- E. de Maat. and R. Winkels. Categorisation of norms. In JURIX 2007, pages 79--88. IOS Press, 2007. Google ScholarDigital Library
- T. Evgeniou and M. Pontil. Regularized multi--task learning. In KDD'04, pages 109--117, 2004. Google ScholarDigital Library
- E. Francesconi. An approach to legal rules modelling and automatic learning. In G. Governatori, editor, JURIX 2009, pages 59--68. IOS Press, 2009. Google ScholarDigital Library
- E. Francesconi, S. Montemagni, W. Peters, and D. Tiscornia. Semantic Processing of Legal Texts, chapter Integrating a Bottom-up and Top-Down Methodology for Building Semantic Resources for the Multilingual Legal Domain, pages 95--121. Number 6036 in LNAI. Springer, Berlin, 2010. Google ScholarDigital Library
- E. Francesconi and A. Passerini. Automatic classification of provisions in legislative texts. AI and Law, 15: 1--17, 2007. Google ScholarDigital Library
- E. Francesconi. and G. Peruginelli. Integrated access to legal literature through automated semantic classification. AI and Law, 17: 31--49, 2008. Google ScholarDigital Library
- M. Grabmair, K. D. Ashley, R. Hwa, and P. M. Sweeney. Toward extracting information from public health statutes using text classification and machine learning. In K. M. Atkinson, editor, JURIX 2011, pages 73--82. IOS Press, 2011.Google Scholar
- N. Kakwani. On a class of poverty measures. Econometria, pages 437--446, 1980.Google ScholarCross Ref
- R. Opsomer, G. D. Meyer, C. Cornelis, and G. van Eetvelde. Exploiting properties of legislative texts to improve classification accuracy. In G. Governatori, editor, JURIX 2009, pages 136--145. IOS Press, 2009. Google ScholarDigital Library
- S. J. Pan and Q. Yang. A survey on transfer learning. TKDE, 22(10): 1345--1359, 2010. Google ScholarDigital Library
- B. Pouliquen, R. Steinberger, and C. Ignat. Automatic annotation of multi-lingual text collections with a conceptual thesaurus. arXiv preprint, 2006.Google Scholar
- R. Steinberger, M. Ebrahim, and C. Ignat. Jrc eurovoc indexer jex-a freely available multi-label categorisation tool. arXiv preprint, 2013.Google Scholar
- P. M. Sweeney, E. E. Bjerke, M. A. Potter, H. Guclu, C. R. Keane, K. D. Ashley, M. Grabmair, and R. Hwa. Network analysis of manually-encoded state laws and prospects for automation. In R. Winkels, N. Lattieri, and S. Faro, editors, Network Analysis in Law, pages 53--78, Napoli, 2014. Diritto Scienza Technologia.Google Scholar
- J. Šavelka, M. Grabmair, and K. D. Ashley. Mining information from statutory texts in multi-jurisdictional settings. In R. Hoekstra, editor, JURIX 2014, pages 133--142. IOS Press, 2014.Google Scholar
- R. Winkels and R. Hoekstra. Automatic extraction of legal concepts and definitions. In JURIX 2012, pages 157--166, 2012.Google Scholar
- A. Wyner and W. Peters. On rule extraction from regulations. In JURIX 2011, pages 113--122. IOS Press, 2011.Google Scholar
Index Terms
- Transfer of predictive models for classification of statutory texts in multi-jurisdictional settings
Recommendations
Automatic classification of provisions in legislative texts
AI & law in eGovernment and eDemocracy part IILegislation usually lacks a systematic organization which makes the management and the access to norms a hard problem to face. A more analytic semantic unit of reference (provision) for legislative texts was identified. A model of provisions (provisions ...
Chinese text classification by the Naïve Bayes Classifier and the associative classifier with multiple confidence threshold values
Each type of classifier has its own advantages as well as certain shortcomings. In this paper, we take the advantages of the associative classifier and the Naive Bayes Classifier to make up the shortcomings of each other, thus improving the accuracy of ...
Online transfer learning with multiple source domains for multi-class classification
AbstractThe major objective of transfer learning is to handle the learning tasks on a target domain by utilizing the knowledge extracted from the source domain(s), when the labeled data in the target domain are not sufficient. Transfer ...
Highlights- An online multi-source multiple classification transfer learning algorithm is proposed.
Comments