mlsanityData to 7 Oct 2026

Word-Level Coreference Resolution

arXiv 2109.04127 ↗First posted 9 Sep 2021cs.CLcited by 40

Not on the map. Why?

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.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 12 of its 22 references that are in the map. First posted on arXiv 9 Sep 2021.

Builds on

12 of 22 references.

References · 12

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2020Longformer: The Long-Document Transformercited by 3,362
  6. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  7. 2017End-to-end Neural Coreference Resolutioncited by 240
  8. 2018Higher-order Coreference Resolution with Coarse-to-fine Inferencecited by 150
  9. 2019Coreference Resolution as Query-based Span Predictioncited by 91
  10. 2020Revealing the Myth of Higher-Order Inference in Coreference Resolutioncited by 49
  11. 2021Coreference Resolution without Span Representationscited by 45
  12. 2018Neural Models for Reasoning over Multiple Mentions using Coreferencecited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 10; 2023: 9; 2024: 12; 2025: 4; 2026: 5.

40 papers.

Sort:

  1. 2022Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gendercited by 47
  2. 2022Autoregressive Structured Prediction with Language Modelscited by 43
  3. 2023Prompting Large Language Models With the Socratic Methodcited by 43
  4. 2022Coreference Resolution through a seq2seq Transition-Based Systemcited by 34
  5. 2022LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolutioncited by 26
  6. 2022F-coref: Fast, Accurate and Easy to Use Coreference Resolutioncited by 23
  7. 2024Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trendscited by 19
  8. 2024Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understandingcited by 16
  9. 2022KnowGL: Knowledge Generation and Linking from Textcited by 13
  10. 2023CAW-coref: Conjunction-Aware Word-level Coreference Resolutioncited by 10
  11. 2023Seq2seq is All You Need for Coreference Resolutioncited by 10
  12. 2024Findings of the Third Shared Task on Multilingual Coreference Resolutioncited by 10
28 more
  1. 2023Improving Automatic Quotation Attribution in Literary Novelscited by 9
  2. 2024Major Entity Identification: A Generalizable Alternative to Coreference Resolutioncited by 9
  3. 2022mOKB6: A Multilingual Open Knowledge Base Completion Benchmarkcited by 7
  4. 2022Mention Annotations Alone Enable Efficient Domain Adaptation for Coreference Resolutioncited by 6
  5. 2024CorPipe at CRAC 2024: Predicting Zero Mentions from Raw Textcited by 6
  6. 2023Visual Storytelling with Question-Answer Planscited by 5
  7. 2025Findings of the Fourth Shared Task on Multilingual Coreference Resolution: Can LLMs Dethrone Traditional Approaches?cited by 5
  8. 2024A Controlled Reevaluation of Coreference Resolution Modelscited by 4
  9. 2024Enhancing Cross-Document Event Coreference Resolution by Discourse Structure and Semantic Informationcited by 4
  10. 2022A Structured Span Selectorcited by 3
  11. 2024Exploring Multiple Strategies to Improve Multilingual Coreference Resolution in CorefUDcited by 3
  12. 2022RuCoCo: a new Russian corpus with coreference annotationcited by 2
  13. 2023Parallel Data Helps Neural Entity Coreference Resolutioncited by 2
  14. 2024Multilingual Coreference Resolution in Low-resource South Asian Languagescited by 2
  15. 2024Transforming Dutch: Debiasing Dutch Coreference Resolution Systems for Non-binary Pronounscited by 2
  16. 2025CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolutioncited by 2
  17. 2026Pantagruel: Unified Self-Supervised Encoders for French Text and Speechcited by 2
  18. 2023Incorporating Singletons and Mention-based Features in Coreference Resolution via Multi-task Learning for Better Generalizationcited by 1
  19. 2023Ensemble Transfer Learning for Multilingual Coreference Resolutioncited by 0
  20. 2023Light Coreference Resolution for Russian with Hierarchical Discourse Featurescited by 0
  21. 2024SPLICE: A Singleton-Enhanced PipeLIne for Coreference REsolutioncited by 0
  22. 2024ThaiCoref: Thai Coreference Resolution Datasetcited by 0
  23. 2025Efficient Seq2seq Coreference Resolution Using Entity Representationscited by 0
  24. 2025BioCoref: Benchmarking Biomedical Coreference Resolution with LLMscited by 0
  25. 2026Beyond Word Boundaries: A Hebrew Coreference Benchmark and an Evaluation Protocol for Morphologically Complex Textcited by 0
  26. 2026One Identity, Many Roles: Multimodal Entity Coreference for Enhanced Video Situation Recognitioncited by 0
  27. 2026Closing the Gap at CRAC 2026: Two-Stage Adaptation for LLM-Based Multilingual Coreference Resolutioncited by 0
  28. 2026CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolutioncited by 0