# Understanding Mention Detector-Linker Interaction in Neural Coreference Resolution

arXiv: https://arxiv.org/abs/2009.09363 · HTML: https://mlsanity.com/paper/2009.09363/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2020.

## Built on by (most cited first, 7 of 7)

- [Moving on from OntoNotes: Coreference Resolution Model Transfer](https://mlsanity.com/paper/2104.08457/) (2021)
- [Are Large Language Models Robust Coreference Resolvers?](https://mlsanity.com/paper/2305.14489/) (2023)
- [Adapting Coreference Resolution Models through Active Learning](https://mlsanity.com/paper/2104.07611/) (2021)
- [Seq2seq is All You Need for Coreference Resolution](https://mlsanity.com/paper/2310.13774/) (2023)
- [Mention Annotations Alone Enable Efficient Domain Adaptation for Coreference Resolution](https://mlsanity.com/paper/2210.07602/) (2022)
- [Incorporating Singletons and Mention-based Features in Coreference Resolution via Multi-task Learning for Better Generalization](https://mlsanity.com/paper/2309.11582/) (2023)
- [Incorporating Constituent Syntax for Coreference Resolution](https://mlsanity.com/paper/2202.10710/) (2022)

## Abstract (arXiv)

Despite significant recent progress in coreference resolution, the quality of current state-of-the-art systems still considerably trails behind human-level performance. Using the CoNLL-2012 and PreCo datasets, we dissect the best instantiation of the mainstream end-to-end coreference resolution model that underlies most current best-performing coreference systems, and empirically analyze the behavior of its two components: mention detector and mention linker. While the detector traditionally focuses heavily on recall as a design decision, we demonstrate the importance of precision, calling for their balance. However, we point out the difficulty in building a precise detector due to its inability to make important anaphoricity decisions. We also highlight the enormous room for improving the linker and show that the rest of its errors mainly involve pronoun resolution. We propose promising next steps and hope our findings will help future research in coreference resolution.