2008 · 116 citations · 32 references
ComputingComputer ScienceComputational LinguisticsInformation RetrievalNatural Language ProcessingCoreference ResolutionCorpus AnnotationLanguage ModelingNamed Entity RecognitionPart-of-speech TaggingMention DetectionRanking Loss
This paper investigates two strategies for improving coreference resolution: (1) training separate models that specialize in particular types of mentions (e.g., pronouns versus proper nouns) and (2) using a ranking loss function rather than a classification function. In addition to being conceptually simple, these modifications of the standard single-model, classification-based approach also deliver significant performance improvements. Specifically, we show that on the ACE corpus both strategies produce f -score gains of more than 3% across the three coreference evaluation metrics (MUC, B 3 , and CEAF).
32
Toward a taxonomy of given-new information
Ellen F. Prince · Medical Entomology and Zoology · 1981 · 1.3K citations
Presupposition Projection as Anaphora Resolution
R.A. van der Sandt · Journal of Semantics · 1992 · 1.1K citations · Full text