Instance-Driven Attachment of Semantic Annotations over Conceptual Hierarchies.

Whether automatically extracted or human generated, open-domain factual knowledge is often available in the form of semantic annotations (e.g., composed-by ) that take one or more specific instances (e.g., rhapsody in blue, george gershwin ) as their arguments. This paper introduces a method for converting flat sets of instance-level annotations into hierarchically organized, concept-level annotations, which capture not only the broad semantics of the desired arguments (e.g., 'People' rather than 'Locations'), but also the correct level of generality (e.g., 'Composers' rather than 'People', or 'Jazz Composers'). The method refrains from encoding features specific to a particular domain or annotation, to ensure immediate applicability to new, previously unseen annotations. Over a gold standard of semantic annotations and concepts that best capture their arguments, the method substantially outperforms three baselines, on average, computing concepts that are less than one step in the hierarchy away from the corresponding gold standard concepts.