Information Extraction and Visualization of Unstructured Textual Data

There is a large amount of textual data on the web that has to be analyzed manually by humans in order to use it in meaningful ways. Techniques that can analyze the data, convert it to meaningful information, connect it with other sources of information, and allow querying would be extremely useful. There are different kinds of textual information available with each kid catering to a different kind of audience. This paper presents an information extraction approach that is a modified traversal algorithm on dependency parse output of text to extract all subject predicate object pairs from text while ensuring that no information is missed out. The output format is designed specifically to fit on a node-edge-node model and form the building blocks of a network that makes understanding of the text and querying of information from corpus quick and intuitive.