Ge(o)Lo(cator): Geographic Information Extraction from Unstructured Text Data and Web Documents

The constantly growing number of websites, web pages, documents and, textual (Big) Data populating the Internet currently represents a massive resource of information and knowledge for various interests and across many different domains. However, the big amount and the complexity of unstructured, natural language textual data implies several issues and difficulties for end users to find a specific, desired pieces of information. In the era of maximum uptake of social networks and media, automatic extraction and retrieval of geographic information is becoming a field of large interest. In this paper, the GeLo system for extracting addresses and geographical coordinates of companies and organizations from their web domains is presented. The information extraction process relies on NLP techniques, specifically Part-Of-Speech-tagging, pattern recognition and annotation. The overall system performances have been manually evaluated against a consistent subset of the extracted URLs database.