# On Generalization in Coreference Resolution

arXiv: https://arxiv.org/abs/2109.09667 · HTML: https://mlsanity.com/paper/2109.09667/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 20 Sep 2021.

## Builds on (most cited first, 21 of 21)

- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [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)
- [Higher-order Coreference Resolution with Coarse-to-fine Inference](https://mlsanity.com/paper/1804.05392/) (2018)
- [Coreference Resolution as Query-based Span Prediction](https://mlsanity.com/paper/1911.01746/) (2019)
- [An Annotated Dataset of Coreference in English Literature](https://mlsanity.com/paper/1912.01140/) (2019)
- [Revealing the Myth of Higher-Order Inference in Coreference Resolution](https://mlsanity.com/paper/2009.12013/) (2020)
- [Multilingual Neural Machine Translation with Language Clustering](https://mlsanity.com/paper/1908.09324/) (2019)
- [Domain Control for Neural Machine Translation](https://mlsanity.com/paper/1612.06140/) (2016)
- [PreCo: A Large-scale Dataset in Preschool Vocabulary for Coreference Resolution](https://mlsanity.com/paper/1810.09807/) (2018)
- [Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks](https://mlsanity.com/paper/2010.02807/) (2020)
- [Neural Models for Reasoning over Multiple Mentions using Coreference](https://mlsanity.com/paper/1804.05922/) (2018)
- [Syntactic Scaffolds for Semantic Structures](https://mlsanity.com/paper/1808.10485/) (2018)
- [Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling](https://mlsanity.com/paper/1906.06893/) (2019)
- [OntoGUM: Evaluating Contextualized SOTA Coreference Resolution on 12 More Genres](https://mlsanity.com/paper/2106.00933/) (2021)
- [Neural Coreference Resolution with Deep Biaffine Attention by Joint Mention Detection and Mention Clustering](https://mlsanity.com/paper/1805.04893/) (2018)
- [A Cluster Ranking Model for Full Anaphora Resolution](https://mlsanity.com/paper/1911.09532/) (2019)
- [Improving Generalization in Coreference Resolution via Adversarial Training](https://mlsanity.com/paper/1908.04728/) (2019)
- [Parser Training with Heterogeneous Treebanks](https://mlsanity.com/paper/1805.05089/) (2018)
- [A Benchmark of Rule-Based and Neural Coreference Resolution in Dutch Novels and News](https://mlsanity.com/paper/2011.01615/) (2020)
- [Rewarding Coreference Resolvers for Being Consistent with World Knowledge](https://mlsanity.com/paper/1909.02392/) (2019)

## Built on by (most cited first, 24 of 24)

- [Large Language Models are Few-Shot Clinical Information Extractors](https://mlsanity.com/paper/2205.12689/) (2022)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks](https://mlsanity.com/paper/2210.10040/) (2022)
- [Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends](https://mlsanity.com/paper/2407.21489/) (2024)
- [Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing](https://mlsanity.com/paper/2205.12640/) (2022)
- [Are Large Language Models Robust Coreference Resolvers?](https://mlsanity.com/paper/2305.14489/) (2023)
- [Seq2seq is All You Need for Coreference Resolution](https://mlsanity.com/paper/2310.13774/) (2023)
- [Major Entity Identification: A Generalizable Alternative to Coreference Resolution](https://mlsanity.com/paper/2406.14654/) (2024)
- [Mention Annotations Alone Enable Efficient Domain Adaptation for Coreference Resolution](https://mlsanity.com/paper/2210.07602/) (2022)
- [Challenges to Evaluating the Generalization of Coreference Resolution Models: A Measurement Modeling Perspective](https://mlsanity.com/paper/2303.09092/) (2023)
- [Improving Bot Response Contradiction Detection via Utterance Rewriting](https://mlsanity.com/paper/2207.11862/) (2022)
- [Information Redundancy and Biases in Public Document Information Extraction Benchmarks](https://mlsanity.com/paper/2304.14936/) (2023)
- [Semi-supervised multimodal coreference resolution in image narrations](https://mlsanity.com/paper/2310.13619/) (2023)
- [A Controlled Reevaluation of Coreference Resolution Models](https://mlsanity.com/paper/2404.00727/) (2024)
- [BOOKCOREF: Coreference Resolution at Book Scale](https://mlsanity.com/paper/2507.12075/) (2025)
- [Multilingual Coreference Resolution in Multiparty Dialogue](https://mlsanity.com/paper/2208.01307/) (2022)
- [Sentence-Incremental Neural Coreference Resolution](https://mlsanity.com/paper/2305.16947/) (2023)
- [Multilingual Coreference Resolution in Low-resource South Asian Languages](https://mlsanity.com/paper/2402.13571/) (2024)
- [Incorporating Singletons and Mention-based Features in Coreference Resolution via Multi-task Learning for Better Generalization](https://mlsanity.com/paper/2309.11582/) (2023)
- [Solving the Challenge Set without Solving the Task: On Winograd Schemas as a Test of Pronominal Coreference Resolution](https://mlsanity.com/paper/2410.09448/) (2024)
- [Findings of the Fifth Shared Task on Multilingual Coreference Resolution: Expanding Datasets for Long-Range Entities](https://mlsanity.com/paper/2605.21369/) (2026)
- [SPLICE: A Singleton-Enhanced PipeLIne for Coreference REsolution](https://mlsanity.com/paper/2403.17245/) (2024)
- [Efficient Seq2seq Coreference Resolution Using Entity Representations](https://mlsanity.com/paper/2510.14504/) (2025)
- [Plug-and-Adapt: Multimodal Coreference Resolution at First Sight with a Pretrained Alignment Model](https://mlsanity.com/paper/2606.17950/) (2026)

## Abstract (arXiv)

While coreference resolution is defined independently of dataset domain, most models for performing coreference resolution do not transfer well to unseen domains. We consolidate a set of 8 coreference resolution datasets targeting different domains to evaluate the off-the-shelf performance of models. We then mix three datasets for training; even though their domain, annotation guidelines, and metadata differ, we propose a method for jointly training a single model on this heterogeneous data mixture by using data augmentation to account for annotation differences and sampling to balance the data quantities. We find that in a zero-shot setting, models trained on a single dataset transfer poorly while joint training yields improved overall performance, leading to better generalization in coreference resolution models. This work contributes a new benchmark for robust coreference resolution and multiple new state-of-the-art results.