Textual data is a core source of information in the enterprise. Example demands arise from sales departments (monitor and identify leads), human resources (identify professionals with capabilities in “xyz”), market research (campaign monitoring from the social web), product development (incorporate feedback from customers), supply chain management (check for product recalls) or from the medical domain (anamnesis). In this talk we introduce two systems: INREX is a declarative relation extraction approach for an in-memory data base system. TASTY is an end-to-end entity recognition approach relying on raw character-based training data and stacked bi-directional LTSMs. We will discuss our experiences from real world scenarios.
Learn more about our projects at https://prof.beuth-hochschule.