Toponym Resolution in Text: “Which Sheffield is it?”

Named entity tagging comprises the sub-tasks of identifying a text span and classifying it, but this view ignores the relationship between the entities and the world. Spatial and temporal entities ground events in space-time, and this relationship is vital for applications such as question answering and event tracking. There is much recent work regarding the temporal dimension [13, 10], but no extensive study of the spatial dimension. I propose to investigate how spatial named entities (which are often referentially ambiguous) can be automatically resolved with respect to an extensional coordinate model (toponym resolution), using hybrid heuristic/statistical methods. The major contributions of this research project are a corpus of text manually annotated for spatial named entities with their model correlates as a training/evaluation resource [4] and a novel method to spatially ground toponyms in text.