GaiusT 2.0: Evolution of a Framework for Annotating Legal Documents

Semantic annotation technologies support the extraction of legal concepts, for example rights and obligations, from legal documents. For software engineers, the final goal is to identify compliance requirements a software system has to fulfill in order to comply with a law or regulation. That implies analyzing and annotating legal documents in prescriptive natural language, still an open problem for research in the field. In this paper we describe GaiusT 2.0, a system for extracting requirements from legal documents. GaiusT 2.0 is the result of the evolution of GaiusT, and has been designed and implemented as a web-based system intended to semi-automate the extraction process. Results of the application of GaiusT 2.0 show that the new version improves performance of the extraction process and also makes the tool more usable.

[1]  Mehrdad Sabetzadeh,et al.  An automated framework for detection and resolution of cross references in legal texts , 2015, Requirements Engineering.

[2]  John Mylopoulos,et al.  GaiusT: supporting the extraction of rights and obligations for regulatory compliance , 2013, Requirements Engineering.

[3]  John Mylopoulos,et al.  Automating the Generation of Semantic Annotation Tools Using a Clustering Technique , 2008, NLDB.

[4]  John Mylopoulos,et al.  Building Large Models of Law with NómosT , 2016, ER.

[5]  Lilly Irani,et al.  Amazon Mechanical Turk , 2018, Advances in Intelligent Systems and Computing.

[6]  Akira Shimazu,et al.  Automated reference resolution in legal texts , 2013, Artificial Intelligence and Law.

[7]  John Mylopoulos,et al.  Cerno: Light-weight tool support for semantic annotation of textual documents , 2009, Data Knowl. Eng..

[8]  Ravikumar Kondadadi,et al.  Named Entity Recognition and Resolution in Legal Text , 2010, Semantic Processing of Legal Texts.

[9]  Rinke Hoekstra,et al.  Automatic Extraction of Legal Concepts and Definitions , 2012, JURIX.

[10]  John Mylopoulos,et al.  Arguing regulatory compliance of software requirements , 2013, Data Knowl. Eng..

[11]  Ana I. Anton,et al.  Legal requirements metrics for compliance analysis , 2012 .

[12]  James R. Cordy,et al.  The TXL source transformation language , 2006, Sci. Comput. Program..

[13]  Livio Robaldo,et al.  NLP Challenges for Eunomos a Tool to Build and Manage Legal Knowledge , 2012, LREC.

[14]  Annie I. Antón,et al.  Analyzing Regulatory Rules for Privacy and Security Requirements , 2008, IEEE Transactions on Software Engineering.

[15]  R. Califf,et al.  Health Insurance Portability and Accountability Act (HIPAA): must there be a trade-off between privacy and quality of health care, or can we advance both? , 2003, Circulation.

[16]  Alessandro Mazzei,et al.  TULSI: an NLP system for extracting legal modificatory provisions , 2012, Artificial Intelligence and Law.

[17]  Radboud Winkels,et al.  Machine Learning versus Knowledge Based Classification of Legal Texts , 2010, JURIX.

[18]  John Mylopoulos,et al.  Capturing Variability of Law with Nómos 2 , 2012, ER.

[19]  John Mylopoulos,et al.  Applying gaiust for extracting requirements from legal documents , 2013, 2013 6th International Workshop on Requirements Engineering and Law (RELAW).

[20]  Ernest Davis.  The Singularity and the State of the Art in Artificial Intelligence: The technological singularity (Ubiquity symposium) , 2014, UBIQ.

[21]  John Mylopoulos,et al.  Applying Software Analysis Technology to Lightweight Semantic Markup of Document Text , 2005, ICAPR.

[22]  Luisa Mich,et al.  Usability issues for systems supporting requirements extraction from legal documents , 2014, 2014 IEEE 7th International Workshop on Requirements Engineering and Law (RELAW).

[23]  John Mylopoulos,et al.  A Lightweight Approach to Semantic Annotation of Research Papers , 2007, NLDB.