We present an unsupervised, nonparametric Bayesian approach to coreference resolution which models both global entity identity across a corpus as well as the sequential anaphoric ...
This paper investigates two strategies for improving coreference resolution: (1) training separate models that specialize in particular types of mentions (e.g., pronouns versus pr...
We present a coreference resolver called BABAR that uses contextual role knowledge to evaluate possible antecedents for an anaphor. BABAR uses information extraction patterns to i...
There have been considerable attempts to incorporate semantic knowledge into coreference resolution systems: different knowledge sources such as WordNet and Wikipedia have been us...
Zhiheng Huang, Guangping Zeng, Weiqun Xu, Asli &Cc...
This paper presents a machine learning approach to the resolution of coreferential relations between nominal constituents in Dutch. It is the first significant automatic approach ...