Light Coreference Resolution for Russian with Hierarchical Discourse Features
This work addresses coreference resolution for Russian, an incremental improvement by adding discourse features to existing models.
The paper tackled coreference resolution in Russian by incorporating rhetorical information from discourse parses into a neural model, achieving 74.6% F1 on the development set and 73.3% F1 on the test set of the RuCoCo-23 Shared Task.
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.