Computational Models of Anaphora

Interpreting anaphoric references is a fundamental aspect of our language competence that has long attracted the attention computational linguists. The appearance ever-larger anaphorically annotated data sets covering more and phenomena in ever-greater detail spurred development increasingly sophisticated models; as result, most recent state-of-the-art neural models are able to achieve impressive performance by leveraging linguistic, lexical, discourse, encyclopedic information. This article provides thorough survey anaphora resolution (coreference) throughout this development, reviewing available both preneural history field and—in detail—current models, including research on less-studied aspects interpretation such bridging reference discourse deixis interpretation.