2013 · 49 citations · 23 references
ComputingComputer ScienceLinguisticsArtificial IntelligenceComputational LinguisticsNatural Language ProcessingAnaphora ResolutionAutomated ReasoningConstraint RepresentationCoreference ResolutionLanguage ModelingLanguage ModelsAntecedent IdentificationBridging Anaphora ResolutionConstraintsGlobal InferenceLocal Feature DescriptorsLocal InferenceMarkov Logic NetworksSyntactic Constraints
We present the first work on antecedent selection for bridging resolution without restrictions on anaphor or relation types. Our model integrates global constraints on top of a rich local feature set in the framework of Markov logic networks. The global model improves over the local one and both strongly outperform a reimplementation of prior work. 1
23