CONDITOR1: Topic Maps and DITA labelling tool for textual documents with historical information

TL;DR

This paper presents Conditor, a tool for labeling and retrieving historical textual information using topic maps and DITA, enhanced by object-oriented databases and integrated search for improved accuracy and future recommender systems.

Contribution

Introduces a novel engine that labels entities in historical texts with a combined XTM-DITA model and improves information retrieval through database integration.

Findings

Effective entity labeling with XTM-DITA model

Enhanced search accuracy using object-oriented database integration

Demonstration of search results in a 3D graphical interface

Abstract

Conditor is a software tool which works with textual documents containing historical information. The purpose of this work two-fold: firstly to show the validity of the developed engine to correctly identify and label the entities of the universe of discourse with a labelled-combined XTM-DITA model. Secondly to explain the improvements achieved in the information retrieval process thanks to the use of a object-oriented database (JPOX) as well as its integration into the Lucene-type database search process to not only accomplish more accurate searches, but to also help the future development of a recommender system. We finish with a brief demo in a 3D-graph of the results of the aforementioned search.