# Stay Together: A System for Single and Split-antecedent Anaphora Resolution

arXiv: https://arxiv.org/abs/2104.05320 · HTML: https://mlsanity.com/paper/2104.05320/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 35 references that are in the map.
- First posted on arXiv 12 Apr 2021.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [WinoGrande: An Adversarial Winograd Schema Challenge at Scale](https://mlsanity.com/paper/1907.10641/) (2019)
- [Higher-order Coreference Resolution with Coarse-to-fine Inference](https://mlsanity.com/paper/1804.05392/) (2018)
- [BERT for Coreference Resolution: Baselines and Analysis](https://mlsanity.com/paper/1908.09091/) (2019)
- [Coreference Resolution as Query-based Span Prediction](https://mlsanity.com/paper/1911.01746/) (2019)
- [Deep Reinforcement Learning for Mention-Ranking Coreference Models](https://mlsanity.com/paper/1609.08667/) (2016)
- [Improving Coreference Resolution by Learning Entity-Level Distributed Representations](https://mlsanity.com/paper/1606.01323/) (2016)
- [Learning Global Features for Coreference Resolution](https://mlsanity.com/paper/1604.03035/) (2016)
- [Resolving Gendered Ambiguous Pronouns with BERT](https://mlsanity.com/paper/1906.01161/) (2019)
- [Bridging Anaphora Resolution as Question Answering](https://mlsanity.com/paper/2004.07898/) (2020)
- [A Cluster Ranking Model for Full Anaphora Resolution](https://mlsanity.com/paper/1911.09532/) (2019)
- [Solving Hard Coreference Problems](https://mlsanity.com/paper/1907.05524/) (2019)
- [Multi-task Learning Based Neural Bridging Reference Resolution](https://mlsanity.com/paper/2003.03666/) (2020)
- [Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution](https://mlsanity.com/paper/2011.00245/) (2020)
- [A Mention-Ranking Model for Abstract Anaphora Resolution](https://mlsanity.com/paper/1706.02256/) (2017)

## Built on by (most cited first, 3 of 3)

- [Moving on from OntoNotes: Coreference Resolution Model Transfer](https://mlsanity.com/paper/2104.08457/) (2021)
- [Mention Annotations Alone Enable Efficient Domain Adaptation for Coreference Resolution](https://mlsanity.com/paper/2210.07602/) (2022)
- [Scoring Coreference Chains with Split-Antecedent Anaphors](https://mlsanity.com/paper/2205.12323/) (2022)

## Abstract (arXiv)

The state-of-the-art on basic, single-antecedent anaphora has greatly improved in recent years. Researchers have therefore started to pay more attention to more complex cases of anaphora such as split-antecedent anaphora, as in Time-Warner is considering a legal challenge to Telecommunications Inc's plan to buy half of Showtime Networks Inc-a move that could lead to all-out war between the two powerful companies. Split-antecedent anaphora is rarer and more complex to resolve than single-antecedent anaphora; as a result, it is not annotated in many datasets designed to test coreference, and previous work on resolving this type of anaphora was carried out in unrealistic conditions that assume gold mentions and/or gold split-antecedent anaphors are available. These systems also focus on split-antecedent anaphors only. In this work, we introduce a system that resolves both single and split-antecedent anaphors, and evaluate it in a more realistic setting that uses predicted mentions. We also start addressing the question of how to evaluate single and split-antecedent anaphors together using standard coreference evaluation metrics.