Project | Intellektix

This project's goal is to develop an information-extraction system with higher coverage and improved accuracy compared to state-of-the-art competitors. The corresponding research area of text analytics has many important applications for today's companies, e.g., monitoring the Internet for new technology trends and the automatic processing and semantic enrichment of business correspondence. The focus of this project is the large-scale utilization of already available domain knowledge. At first, this domain knowledge will be exploited for unsupervised training-example generation, enabling a potentially high coverage in the recognition of events and relations in texts. Later, the domain knowledge will be used to check extracted candidate knowledge for plausibility and logical consistency.