A neural Entity Coreference Resolution review

Nikolaos Stylianou, Ioannis P. Vlahavas

Abstract: Highlights • We categorize the methodologies based on their model types and novelties. • We review Pronoun Resolution and emphasize its relation to Coreference Resolution. • We provide a classification of available datasets based on text styles and variety. • We perform an analysis of the available evaluation metrics of Coreference Resolution. • We outline the anaphoric types and constraints in Coreference Resolution. Abstract Entity Coreference Resolution is the task of resolving all mentions in a document that refer to the same real world entity and is considered as one of the most difficult tasks in natural language understanding. It is of great importance for downstream natural language processing tasks such as entity linking, machine translation, summarization, chatbots, etc. This work aims to give a detailed review of current progress on solving Coreference Resolution using neural-based approaches. It also provides a detailed appraisal of the datasets and evaluation metrics in the field, as well as the subtask of Pronoun Resolution that has seen various improvements in the recent years. We highlight the advantages and disadvantages of the approaches, the challenges of the task, the lack of agreed-upon standards in the task and propose a way to further expand the boundaries of the field.