Coreference systems are driven by syntactic, semantic, and discourse constraints. We present a simple approach which completely modularizes these three aspects. In contrast to muc...
Abstract. In this paper, we present a systematic evaluation of a hybrid approach of combined rule-based filtering and machine learning to Dutch coreference resolution. Through the...
Machine learning approaches to coreference resolution are typically supervised, and require expensive labeled data. Some unsupervised approaches have been proposed (e.g., Haghighi...
A model for reference use in communication is proposed, from a representationist point of view. Both the sender and the receiver of a message handle representations of their commo...
We show how global constraints such as transitivity can be treated intensionally in a Zero-One Integer Linear Programming (ILP) framework which is geared to find the optimal and c...