The task of coreference resolution has attracted considerable attention in the literature due to its importance in deep language understanding and its potential as a subtask in a variety of complex natural language processing problems. In this study, we outlined the field’s terminology, describe existing metrics, their differences and shortcomings, as well as the available corpora and external resources. We analyzed existing state-of-the-art models and approaches, and reviewed recent advances and trends in the field, namely end-to-end systems that jointly model different subtasks of coreference resolution, and cross-lingual systems that aim to overcome the challenges of less-resourced languages. Finally, we discussed the main challenges and open issues faced by coreference resolution systems.

André Ferreira Cruz, Gil Rocha, Henrique Lopes Cardoso. Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda. 2019.

The task of coreference resolution has attracted a great deal of attention in the literature due to its importance in deep language understanding, and its potential as a subtask in a variety of complex natural language processing problems. We experiment with different methods for generating training data and architectures for extracting meaningful mention representations. Coreference resolution in lesser-resourced languages is challenging, and transfer learning is a promising technique to overcome the comparatively smaller available corpora. We explore direct transfer learning from Spanish to Portuguese. We present state-of-the-art systems on both Spanish and Portuguese, and report promising results in a cross-language setting.