Speaker: Claudia Bretschneider, Siemens AG

Title: Information Extraction from Biomedical Texts and Images

UIMA stands for Unstructured Information Management Architecture. UIMA is to date the only accepted industry standard for content analytics and semantic annotation. Other general frameworks used for natural language processing include the General Architecture for Text Engineering (GATE) and the Natural Language Toolkit (NLTK).
Their availability is important because we have become overwhelmed by the sheer amount of multimedia material--big data--produced without having a gold standard for the extraction of structured information. Content-based information access has changed, now we tackle information encoded in heterogeneous media, such as texts and images. The talk focuses on  Siemens' current investigations on Information Extraction from Biomedical Texts and Images and describes special architectural decisions and specific implementations of semantic annotators that have been created.