An incremental entity-mention model for coreference resolution with restrictive antecedent accessibility

Abstract

We introduce an incremental entity-mention model for coreference resolution. Our experiments show that it is superior to a non-incremental version in the same environment. The benefits of an incremental architecture are: a reduction of the number of candidate pairs, a means to overcome the problem of underspecified items in pairwise classification and the natural integration of global constraints such as transitivity. Additionally, we have defined a simple salience measure that - coupled with the incremental model - proved to establish a challenging baseline which seems to be on par with machine learning based systems of the 2010's SemEval shared task.