Resumen
In knowledge representation systems for Cultural Heritage (CH) there is a vast amount of curated textual information for CH objects and sites. However, the large-scale study of the accumulated knowledge is difficult as long as it is provided in the form of free text. By extracting the most significant pieces of information from textual descriptions of CH objects and sites and compiling them in a single comprehensive knowledge graph, conforming to a standard would facilitate its exploitation from multiple perspectives including study, presentation and narratives. The method proposed by this research work was to employ Natural Language Processing, and reinforcement learning for semantic knowledge extraction, and a knowledge representation standard of the CH domain for the knowledge graph thus making the extracted knowledge directly compatible with linked open data platforms and CH representation systems.