On Generalization in Coreference Resolution
Shubham Toshniwal, Patrick Xia, Sam Wiseman, Karen Livescu, Kevin Gimpel · 2021
While coreference resolution is defined independently of dataset domain, most models for performing coreference resolution do not transfer well to unseen domains.We consolidate a set of 8 coreference resolution datasets targeting different domains to evaluate the offthe-shelf performance of models.We then mix three datasets for training; even though their domain, annotation guidelines, and metadata differ, we propose a method for jointly training a single model on this heterogeneous data mixture by using data augmentation to account for annotation differences and sampling to balance the data quantities.We find that in a zeroshot setting, models trained on a single dataset transfer poorly while joint training yields improved overall performance, leading to better generalization in coreference resolution models.This work contributes a new benchmark for robust coreference resolution and multiple new state-of-the-art results. 1