Information extraction module provides statistical and ruled-based methods for extracting new knowledge from text content.
Supported functionality includes text decomposition into sentences, phrases and tokens, part-of-speech tagging, and extraction of named entities such as people, organizations, geographical, or time information. Various additional text transformations such as stop word filtering and stemming are also performed.
Full support for English and German is available out-of-the-box while support for additional languages has to be learned by the module. User feedback further refines the information extraction process.