Analyzing the use of dynamic weights in legal case based system

Authors:
Tania C. D. Bueno;Andre Bortolon;Hugo C. Hoeschl;Eduardo S. Mattos;Marcelo S. Ribeiro
Affiliations:
Federal University of Santa Catarina, Florianópolis, SC, Brazil;Federal University of Santa Catarina, Florianópolis, SC, Brazil;Ijuris, Florianópolis, SC, Brazil;Web Intelligence Systems S/A, Florianópolis, SC, Brazil;Web Intelligence Systems S/A, Florianópolis, SC, Brazil
Venue:
ICAIL '03 Proceedings of the 9th international conference on Artificial intelligence and law
Year:
2003

Citing 4
Cited 0

Case-based reasoning: foundational issues, methodological variations, and system approaches

AI Communications
JurisConsulto: retrieval in jurisprudencial text bases using juridical terminology

ICAIL '99 Proceedings of the 7th international conference on Artificial intelligence and law
Olimpo: contextual structured search to improve the representation of UN security council resolutions with information extraction methods

Proceedings of the 8th international conference on Artificial intelligence and law
CBR for Document Retrieval: The FALLQ Project

ICCBR '97 Proceedings of the Second International Conference on Case-Based Reasoning Research and Development

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a case-based system to retrieve legal statements of Brazilian High Courts that emphasizes the use of theoretical structures to represent cases. AlphaThemis system has the characteristics from other case-based systems. The major innovation is to allow the user modify the weights used to determine the importance of each feature in similarity measure. This innovation is called dynamic weights. Their objective is to improve the retrieval accuracy in systems that have a human expert supporting the case base creation. In this paper, we analyze the recall and usefulness of dynamic weights, suggesting a new calibration of attribute relevance to achieve the their total efficiency.