Home // ICCGI 2012, The Seventh International Multi-Conference on Computing in the Global Information Technology // View article

Knowledge-Based Visualization of Textual Information Applied in Biomedical Text Mining

Authors:
Joseph Leone
Dong-Guk Shin

Keywords: Text visualization; document visualization; natural language processing; text; semantic processing; dynamic ontology development; collaboration system; information retrieval; search; biomedical literature mining; gene regulatory relationships; cell signal

Abstract:
This paper describes a system, called VisuText, which creates visualized diagrams from textual descriptions. This work was motivated by the awareness that if additional contextual knowledge is appropriately utilized, one can develop a visualization system that systematically translates recognized objects and their relationships into a collection of one or more cohesively assembled pictures. VisuText first translates text into a computable representation, called SP form. SP forms are then converted into schematic diagrams by combining words and appropriate small images which themselves are stitched together to form a bigger meaningful picture. VisuText is especially suited for visualizing text that describes processes, particularly, those expressing similar facts and relationships in a large quantity. We find one excellent application area of VisuText is using it as a post-processing step after gene regulatory relationships are extracted through text mining of biomedical literature to pictorially represent discovered gene regulatory relationships for easier understanding by biomedical scientists. We illustrate how VisuText works by creating a pictorial representation of gene regulatory relationships from a set of statements extracted from the biomedical literature.

Pages: 107 to 112

Copyright: Copyright (c) IARIA, 2012

Publication date: June 24, 2012

Published in: conference

ISSN: 2308-4529

ISBN: 978-1-61208-202-8

Location: Venice, Italy

Dates: from June 24, 2012 to June 29, 2012