A twin-model is proposed for coreference resolution: a link component, modeling the coreferential relationship between an anaphor and a candidate antecedent, and a creation compon...
We investigate the effect of encoding additional semantic and syntactic information sources in a classification-based machine learning approach to the task of coreference resolutio...
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...
Traditional learning-based coreference resolvers operate by training a mentionpair classifier for determining whether two mentions are coreferent or not. Two independent lines of ...
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 ...