An Entity Based Model for Coreference Resolution

Recently, many advanced machine learning approaches have been proposed for coreference resolution; however, all of the discriminatively-trained models reason over mentions rather than entities. That is, they do not explicitly contain vari- ables indicating the "canonical" values for each attribute of an entity (e.g., name, venue, title, etc.). This canonical- ization step is typically implemented as a post-processing routine to coreference resolution prior to adding the ex- tracted entity to a database. In this paper, we propose a discriminatively-trained model that jointly performs corefer- ence resolution and canonicalization, enabling features over hypothesized entities. We validate our approach on two different coreference problems: newswire anaphora resolu- tion and research paper citation matching, demonstrating im- provements in both tasks and achieving an error reduction of up to 62% when compared to a method that reasons about mentions only.