# Multi-task Learning Based Neural Bridging Reference Resolution

arXiv: https://arxiv.org/abs/2003.03666 · HTML: https://mlsanity.com/paper/2003.03666/

## Key facts

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

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

- [Scoring Coreference Chains with Split-Antecedent Anaphors](https://mlsanity.com/paper/2205.12323/) (2022)
- [Stay Together: A System for Single and Split-antecedent Anaphora Resolution](https://mlsanity.com/paper/2104.05320/) (2021)
- [End-to-end Neural Information Status Classification](https://mlsanity.com/paper/2109.02753/) (2021)
- [Incorporating Singletons and Mention-based Features in Coreference Resolution via Multi-task Learning for Better Generalization](https://mlsanity.com/paper/2309.11582/) (2023)
- [Integrating knowledge bases to improve coreference and bridging resolution for the chemical domain](https://mlsanity.com/paper/2404.10696/) (2024)
- [Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures](https://mlsanity.com/paper/2505.11726/) (2025)
- [LLMBridge: An LLM Pipeline for End-to-end Referential Bridging Resolution in English](https://mlsanity.com/paper/2605.29048/) (2026)

## Abstract (arXiv)

We propose a multi task learning-based neural model for resolving bridging references tackling two key challenges. The first challenge is the lack of large corpora annotated with bridging references. To address this, we use multi-task learning to help bridging reference resolution with coreference resolution. We show that substantial improvements of up to 8 p.p. can be achieved on full bridging resolution with this architecture. The second challenge is the different definitions of bridging used in different corpora, meaning that hand-coded systems or systems using special features designed for one corpus do not work well with other corpora. Our neural model only uses a small number of corpus independent features, thus can be applied to different corpora. Evaluations with very different bridging corpora (ARRAU, ISNOTES, BASHI and SCICORP) suggest that our architecture works equally well on all corpora, and achieves the SoTA results on full bridging resolution for all corpora, outperforming the best reported results by up to 36.3 p.p..