Toponym
Resolution in Text
Jochen Leidner
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 Topic Detection andTracking.
Much recent work has addressed the temporal dimension
(Setzer and Gaizauskas, 2002; Mani & Wilson, 2000), but no extensive
study of the spatial dimension. We 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 (Leidner, 2004) and a novel
method to spatially ground toponyms in text.