The IST project SEKT (Semantically Enabled Knowledge Technologies) aims at developing semantic technologies by integrating knowledge management, text mining, and human language technology. Tools and methodologies implemented in the SEKT project are employed and optimized in three case studies, one of them being concerned with intelligent integrated decision support for legal professionals. The main goal of this case study is to offer decision support to newly appointed judges in Spain by means of iFAQ, an intelligent Frequently Asked Questions system based on a complex ontology of the legal domain. Building this ontology is a tedious and time-consuming task requiring profound knowledge of legal documents and language. Therefore, any kind of automatic support can significantly increase the efficiency of the knowledge acquisition process. In this paper we present Text2Onto, an open-source tool for ontology learning, and our experiments with legal case study data. The previously existing English version of Text2Onto has been adapted to support the linguistic analysis of Spanish texts, including language-specific algorithms for the extraction of ontological concepts, instances and relations. Text2Onto greatly facilitated the automatic generation of the initial version of the Spanish legal ontology from a given collection of Spanish documents. In further iterative steps which included a mixture of learning and manual effort the ontology has been refined and applied to the real-world case study.
[1]
Guiraude Lame,et al.
Using NLP Techniques to Identify Legal Ontology Components: Concepts and Relations
,
2004,
Artificial Intelligence and Law.
[2]
Johanna Völker,et al.
Towards large-scale, open-domain and ontology-based named entity classification
,
2005
.
[3]
Paulo Quaresma,et al.
A Methodology to Create Legal Ontologies in a Logic Programming Based Web Information Retrieval System
,
2004,
Artificial Intelligence and Law.
[4]
Christiane Fellbaum,et al.
Book Reviews: WordNet: An Electronic Lexical Database
,
1999,
CL.
[5]
Steffen Staab,et al.
Gimme' the context: context-driven automatic semantic annotation with C-PANKOW
,
2005,
WWW '05.
[6]
Vito Pirrelli,et al.
NLP-based Ontology Learning from Legal Texts. A Case Study
,
2007,
LOAIT.
[7]
Manfred Pinkal,et al.
Computational linguistic support for legal ontology construction
,
2005,
ICAIL '05.
[8]
Johanna Völker,et al.
A Framework for Ontology Learning and Data-driven Change Discovery
,
2005
.