Home // IMMM 2016, The Sixth International Conference on Advances in Information Mining and Management // View article

Automatic City Knowledge Discovery from Internet Resources

Authors:
Nazanin Firoozeh

Keywords: Urban Simulation; Knowledge Discovery; Common Sense Knowledge

Abstract:
Knowledge Discovery plays an important role in the Artificial Intelligence field. Due to the growing nature of the Web, using proper sources of extraction and reducing human intervention is an important step towards creating rich knowledge bases. Urban simulations are one type of Interactive Virtual Environment, which attempt to represent dynamic processes and interactions of urban development. Making these virtual environments closer to the human behaviour requires rich sources of knowledge. This paper presents a pattern-based approach for knowledge extraction. The goal is to extract the implicit knowledge behind any given city-related text. To achieve this goal, we make use of category names and infobox tables from Wikipedia. The system takes two inputs: 1. a text/Uniform Resource Locator (URL), 2. set of extraction patterns. Comparing to some of the proposed tools in the state-of-the-art, our system uses a simpler approach which reduces the human intervention. We tested the system with different text inputs and represented the results as both a text file and a set of triples. Manual evaluation of the system showed its good performance. According to the results, category names are a good resource of common sense knowledge when compared to infobox tables, which mostly contain basic knowledge.

Pages: 18 to 25

Copyright: Copyright (c) IARIA, 2016

Publication date: May 22, 2016

Published in: conference

ISSN: 2326-9332

ISBN: 978-1-61208-477-0

Location: Valencia, Spain

Dates: from May 22, 2016 to May 26, 2016