Traditional learning-based coreference resolvers operate by training a mentionpair classifier for determining whether two mentions are coreferent or not. Two independent lines of ...
Most coreference resolution models determine if two mentions are coreferent using a single function over a set of constraints or features. This approach can lead to incorrect deci...
Machine learning approaches to coreference resolution are typically supervised, and require expensive labeled data. Some unsupervised approaches have been proposed (e.g., Haghighi...
We present a supervised learning approach to identification of anaphoric and non-anaphoric noun phrases and show how such information can be incorporated into a coreference resolu...
Standard pairwise coreference resolution systems are subject to errors resulting from their performing anaphora identification as an implicit part of coreference resolution. In t...