# Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution

arXiv: https://arxiv.org/abs/2011.00245 · HTML: https://mlsanity.com/paper/2011.00245/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 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)
- [Few-Shot Anaphora Resolution in Scientific Protocols via Mixtures of In-Context Experts](https://mlsanity.com/paper/2210.03690/) (2022)
- [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)
- [What does the Failure to Reason with "Respectively" in Zero/Few-Shot Settings Tell Us about Language Models?](https://mlsanity.com/paper/2305.19597/) (2023)
- [Can LLMs Detect Ambiguous Plural Reference? An Analysis of Split-Antecedent and Mereological Reference](https://mlsanity.com/paper/2510.04581/) (2025)
- [A Circuit for Plural Reference: How LLMs Represent and Retrieve Singular and Plural Entities](https://mlsanity.com/paper/2609.03687/) (2026)

## Abstract (arXiv)

Now that the performance of coreference resolvers on the simpler forms of anaphoric reference has greatly improved, more attention is devoted to more complex aspects of anaphora. One limitation of virtually all coreference resolution models is the focus on single-antecedent anaphors. Plural anaphors with multiple antecedents-so-called split-antecedent anaphors (as in John met Mary. They went to the movies) have not been widely studied, because they are not annotated in ONTONOTES and are relatively infrequent in other corpora. In this paper, we introduce the first model for unrestricted resolution of split-antecedent anaphors. We start with a strong baseline enhanced by BERT embeddings, and show that we can substantially improve its performance by addressing the sparsity issue. To do this, we experiment with auxiliary corpora where split-antecedent anaphors were annotated by the crowd, and with transfer learning models using element-of bridging references and single-antecedent coreference as auxiliary tasks. Evaluation on the gold annotated ARRAU corpus shows that the out best model uses a combination of three auxiliary corpora achieved F1 scores of 70% and 43.6% when evaluated in a lenient and strict setting, respectively, i.e., 11 and 21 percentage points gain when compared with our baseline.