Background: Like text in other domains, biomedical documents contain a range of terms with more than one possible meaning. These ambiguities form a significant obstacle to the aut...
Mark Stevenson, Yikun Guo, Robert J. Gaizauskas, D...
Learning visual classifiers for object recognition from weakly labeled data requires determining correspondence between image regions and semantic object classes. Most approaches u...
Probabilistic grammars offer great flexibility in modeling discrete sequential data like natural language text. Their symbolic component is amenable to inspection by humans, while...
Digital libraries can take advantage of documents that have their content (semantics) explicitly represented as knowledge structures. These knowledge-rich documents can be created ...
Intelligent access to information requires semantic integration of structured databases with unstructured textual resources. While the semantic integration problem has been widely...