From Textual Information Sources to Linked Data in the Agatha Project

TL;DR

This paper presents a pipeline for converting Portuguese textual documents into linked data using ontologies and NLP techniques, enabling reasoning in the domain of criminal investigations.

Contribution

It introduces a language-independent architecture that combines NLP modules with ontologies to represent and reason about textual data in Portuguese.

Findings

Successful ontology population from Portuguese texts

Language-independent NLP pipeline architecture

Potential for reasoning in criminal investigation domain

Abstract

Automatic reasoning about textual information is a challenging task in modern Natural Language Processing (NLP) systems. In this work we describe our proposal for representing and reasoning about Portuguese documents by means of Linked Data like ontologies and thesauri. Our approach resorts to a specialized pipeline of natural language processing (part-of-speech tagger, named entity recognition, semantic role labeling) to populate an ontology for the domain of criminal investigations. The provided architecture and ontology are language independent. Although some of the NLP modules are language dependent, they can be built using adequate AI methodologies.