# Word-Level Coreference Resolution

arXiv: https://arxiv.org/abs/2109.04127 · HTML: https://mlsanity.com/paper/2109.04127/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 9 Sep 2021.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [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)
- [Revealing the Myth of Higher-Order Inference in Coreference Resolution](https://mlsanity.com/paper/2009.12013/) (2020)
- [Coreference Resolution without Span Representations](https://mlsanity.com/paper/2101.00434/) (2021)
- [Neural Models for Reasoning over Multiple Mentions using Coreference](https://mlsanity.com/paper/1804.05922/) (2018)

## Built on by (most cited first, 30 of 40)

- [Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gender](https://mlsanity.com/paper/2202.11923/) (2022)
- [Autoregressive Structured Prediction with Language Models](https://mlsanity.com/paper/2210.14698/) (2022)
- [Prompting Large Language Models With the Socratic Method](https://mlsanity.com/paper/2303.08769/) (2023)
- [Coreference Resolution through a seq2seq Transition-Based System](https://mlsanity.com/paper/2211.12142/) (2022)
- [LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution](https://mlsanity.com/paper/2205.12644/) (2022)
- [F-coref: Fast, Accurate and Easy to Use Coreference Resolution](https://mlsanity.com/paper/2209.04280/) (2022)
- [Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends](https://mlsanity.com/paper/2407.21489/) (2024)
- [Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding](https://mlsanity.com/paper/2410.01671/) (2024)
- [KnowGL: Knowledge Generation and Linking from Text](https://mlsanity.com/paper/2210.13952/) (2022)
- [CAW-coref: Conjunction-Aware Word-level Coreference Resolution](https://mlsanity.com/paper/2310.06165/) (2023)
- [Seq2seq is All You Need for Coreference Resolution](https://mlsanity.com/paper/2310.13774/) (2023)
- [Findings of the Third Shared Task on Multilingual Coreference Resolution](https://mlsanity.com/paper/2410.15949/) (2024)
- [Improving Automatic Quotation Attribution in Literary Novels](https://mlsanity.com/paper/2307.03734/) (2023)
- [Major Entity Identification: A Generalizable Alternative to Coreference Resolution](https://mlsanity.com/paper/2406.14654/) (2024)
- [mOKB6: A Multilingual Open Knowledge Base Completion Benchmark](https://mlsanity.com/paper/2211.06959/) (2022)
- [Mention Annotations Alone Enable Efficient Domain Adaptation for Coreference Resolution](https://mlsanity.com/paper/2210.07602/) (2022)
- [CorPipe at CRAC 2024: Predicting Zero Mentions from Raw Text](https://mlsanity.com/paper/2410.02756/) (2024)
- [Findings of the Fourth Shared Task on Multilingual Coreference Resolution: Can LLMs Dethrone Traditional Approaches?](https://mlsanity.com/paper/2509.17796/) (2025)
- [Visual Storytelling with Question-Answer Plans](https://mlsanity.com/paper/2310.05295/) (2023)
- [A Controlled Reevaluation of Coreference Resolution Models](https://mlsanity.com/paper/2404.00727/) (2024)
- [Enhancing Cross-Document Event Coreference Resolution by Discourse Structure and Semantic Information](https://mlsanity.com/paper/2406.15990/) (2024)
- [A Structured Span Selector](https://mlsanity.com/paper/2205.03977/) (2022)
- [Exploring Multiple Strategies to Improve Multilingual Coreference Resolution in CorefUD](https://mlsanity.com/paper/2408.16893/) (2024)
- [CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution](https://mlsanity.com/paper/2509.17858/) (2025)
- [RuCoCo: a new Russian corpus with coreference annotation](https://mlsanity.com/paper/2206.04925/) (2022)
- [Parallel Data Helps Neural Entity Coreference Resolution](https://mlsanity.com/paper/2305.17709/) (2023)
- [Multilingual Coreference Resolution in Low-resource South Asian Languages](https://mlsanity.com/paper/2402.13571/) (2024)
- [Transforming Dutch: Debiasing Dutch Coreference Resolution Systems for Non-binary Pronouns](https://mlsanity.com/paper/2405.00134/) (2024)
- [Pantagruel: Unified Self-Supervised Encoders for French Text and Speech](https://mlsanity.com/paper/2601.05911/) (2026)
- [Incorporating Singletons and Mention-based Features in Coreference Resolution via Multi-task Learning for Better Generalization](https://mlsanity.com/paper/2309.11582/) (2023)

## Abstract (arXiv)

Recent coreference resolution models rely heavily on span representations to find coreference links between word spans. As the number of spans is O(n2) in the length of text and the number of potential links is O(n4), various pruning techniques are necessary to make this approach computationally feasible. We propose instead to consider coreference links between individual words rather than word spans and then reconstruct the word spans. This reduces the complexity of the coreference model to O(n2) and allows it to consider all potential mentions without pruning any of them out. We also demonstrate that, with these changes, SpanBERT for coreference resolution will be significantly outperformed by RoBERTa. While being highly efficient, our model performs competitively with recent coreference resolution systems on the OntoNotes benchmark.