Johns Hopkins University
Relation extraction systems are the backbone of many end-user applications, including question answering, web search and clinical text analysis. Advances in machine learning have led to new neural models for learning effective representations directly from data. Yet for many tasks, years of research have created hand-engineered features that yield state of the art performance. This is the case in relation extraction, in which a system consumes natural language and produces a structured machine readable representation of relationships between entities.
Mark will present feature-rich compositional models that combine both hand-engineered features with learned text representations to achieve new state-of-the-art results for relation extraction. These models are widely applicable to problems within natural language processing and beyond. Additionally, he will survey how these models fit into his broader research program by highlighting work by his group on developing new machine learning methods for extracting public health information from clinical and social media text.