Hypatia: An expert system proposal for documentation departments

Abstract

Nowadays, the vast amount of text-based information stored in organizations requires different approaches and new tools in order to manage it adequately. This paper presents Hypatia, a support expert system for documentation departments and regular users that exploits not only local information, but also external resources from the Web (e.g., Linked Data). The expert system uses different modules: Natural Language Processing (NLP) analysis, categorization, semantic disambiguation, Automatic Query Expansion (AQE), semantic search, summarization, knowledge extraction, and aggregation. Users can interact with the expert system in different ways, varying from giving very specific orders to writing a simple list of keywords. The latter method requires a previous interpretation before deciding the response of the system. The obtained results will benefit from semantic links referencing complementary data to improve both the information presentation and the data navigation.

NEREA: Named Entity Recognition and Disambiguation Exploiting Local Document Repositories

“…If we place these works in the context of creating infoboxes in a local document database, more control over customizing the construction of these infoboxes, or even the definition of templates, is missing. Moreover, the generation of infoboxes should also benefit from the use of the local resources for classifying and tagging, like taxonomies, thesaurus, or ontologies, as we have proposed in previous proposals such as [22] and [23]. Finally, it is also necessary to use information extraction tools able to obtain data concerning the entities, both from the local repository and from open and global repositories located on the Web.…”