Coreference resolution is the task of identifying and grouping mentions referring to the same real-world entity. Previous neural models have mainly focused on learning span representations and pairwise scores for coreference decisions. However, current methods do not explicitly capture the referential choice in the hierarchical discourse, an important factor in coreference resolution. In this study, we propose a new approach that incorporates rhetorical information into neural coreference resolution models. We collect rhetorical features from automated discourse parses and examine their impact. As a base model, we implement an end-to-end span-based coreference resolver using a partially fine-tuned multilingual entity-aware language model LUKE. We evaluate our method on the RuCoCo-23 Shared Task for coreference resolution in Russian. Our best model employing rhetorical distance between mentions has ranked 1st on the development set (74.6% F1) and 2nd on the test set (73.3% F1) of the Shared Task. We hope that our work will inspire further research on incorporating discourse information in neural coreference resolution models.
DOI: 10.28995/2075-7182-2023-22-34-41
Download the article (PDF) at the Dialogue 2023 conference website: https://www.dialog-21.ru/media/5887/chistovaeplussmirnovi109.pdf
Download conference proceedings (PDF) at the Dialogue 2023 website: https://www.dialog-21.ru/digest/2023/articles/
Download the article (PDF) at arXiv.org: https://arxiv.org/abs/2306.01465
The code and models are available at GitHub: https://github.com/tchewik/corefhd
Elena Chistova and Ivan Smirnov. Light Coreference Resolution for Russian with Hierarchical Discourse Features // Computational Linguistics and Intellectual Technologies: Proceedings of the International Conference “Dialogue 2023”. June 14–16, 2023. Pp. 34–41.