Geospatial Knowledge Hypercube
Author(s): Zhaonan Wang
Today a tremendous amount of geospatial knowledge is hidden in massive volumes of text data (e.g., news reports, research papers, and social media). To facilitate flexible and powerful geospatial analysis and applications, we introduce a new architecture: geospatial knowledge hypercube, a multi-scale, multidimensional knowledge structure that integrates information from geospatial dimensions, thematic themes and diverse application semantics, computed and extracted from massive spatial-related text data. To construct such a knowledge hypercube, weakly supervised machine learning approaches need to be developed for automatic, dynamic and incremental extraction of heterogeneous geospatial data, thematic themes, latent connections and relationships, and application semantics, through combining a variety of information from unstructured text, structured tables, maps, and image data. The hypercube lays a foundation for many knowledge discovery and in-depth statistical analysis, and other advanced applications. The cube construction will also need to develop new methods for recognizing geospatial entities and inferring geospatial relationships. In this demo, we introduce a knowledge extraction system for automatic hypercube construction, which has been deployed for public access.
Keywords: Named Entity Recognition, Text Classification, Knowledge Extraction System