Publication at Faculty of Mathematics and Physics |
2014
Abstract
We address the task of detection and classification of references in Czech court decisions, mainly we focus on references to other court decisions and acts. We handle these references like entities in the task of Named Entity Recognition.
In addition, we are interested in detection of institutions that issued documents under consideration. Attributes like the applicability of law have been studied as well.
We approach the task using machine learning methods, namely HMM and Perceptron algorithm. We report F-measure over 90% for each entity.
The results significantly outperform the systems published previously.