We present an adaptive clustering model for coreference resolution in which the expert rules of a state of the art deterministic system are used as features over pairs of clusters. A significant advantage of the new approach is that new features can be easily added to the system. We demonstrate this advantage by incorporating semantic compatibility features for neutral pronouns computed from web n-gram statistics. Experimental results show that the combination of the new features with the expert rules in the adaptive clustering approach results in an overall performance improvement and a substantial 5% improvement in F_1 measure for the target pronouns.
展开▼