Improving Generalization in Coreference Resolution via Adversarial Training [article]

Sanjay Subramanian, Dan Roth
2019 arXiv   pre-print
In order for coreference resolution systems to be useful in practice, they must be able to generalize to new text. In this work, we demonstrate that the performance of the state-of-the-art system decreases when the names of PER and GPE named entities in the CoNLL dataset are changed to names that do not occur in the training set. We use the technique of adversarial gradient-based training to retrain the state-of-the-art system and demonstrate that the retrained system achieves higher
more » ... on the CoNLL dataset (both with and without the change of named entities) and the GAP dataset.
arXiv:1908.04728v1 fatcat:bngypk5al5fj5emdk47somhen4