2006 · 132 citations · 16 references
ComputingComputer ScienceLinguisticsComputational LinguisticsMachine LearningNatural Language ProcessingAnaphora ResolutionCoreference ResolutionNamed Entity RecognitionParsingSyntactic AnalysisSyntactic ParsingBenchmark DatasetsParse Tree TheoryPronoun RecognitionStatistical ParsingSyntactic BootstrappingSyntactic ConstraintsSyntactic Constraints On Anaphora
We present an approach to pronoun resolution based on syntactic paths. Through a simple bootstrapping procedure, we learn the likelihood of coreference between a pronoun and a candidate noun based on the path in the parse tree between the two entities. This path information enables us to handle previously challenging resolution instances, and also robustly addresses traditional syntactic coreference constraints. Highly coreferent paths also allow mining of precise probabilistic gender/number information. We combine statistical knowledge with well known features in a Support Vector Machine pronoun resolution classifier. Significant gains in performance are observed on several datasets.
16
Making Large-Scale SVM Learning Practical
Thorsten Joachims · Technical reports · 2006 · 4.3K citations · Full text
Word association norms, mutual information, and lexicography
Kenneth Church, Patrick Hanks · 1990 · 3.7K citations
An algorithm for pronominal anaphora resolution
Shalom Lappin, Herbert J. Leass · 1994 · 765 citations