Separately Parameterizing Singleton Detection Improves End-to-end Neural Coreference Resolution.
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Short Papers, 2024
CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
A Controlled Reevaluation of Coreference Resolution Models.
Proceedings of the 2024 Joint International Conference on Computational Linguistics, 2024