---
title: "F-coref: Fast, Accurate and Easy to Use — Otmazgin 2022"
description: "Coreference resolution groups mentions in a text that point to the same entity."
authors: ["Shon Otmazgin", "Arie Cattan", "Yoav Goldberg"]
year: 2022
venue: "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations"
source: "https://aclanthology.org/2022.aacl-demo.6/"
doi: "10.18653/v1/2022.aacl-demo.6"
arxiv: "2209.04280"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/otmazgin-2022-f-coref-fast-accurate-easy/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/otmazgin-2022-f-coref-fast-accurate-easy/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2022](https://md.research.elamur.ai/free/papers/2022/) / F-coref: Fast, Accurate and Easy to Use Coreference Resolution

# F-coref: Fast, Accurate and Easy to Use Coreference Resolution

**Authors:** [Shon Otmazgin](https://md.research.elamur.ai/free/authors/shon-otmazgin/), [Arie Cattan](https://md.research.elamur.ai/free/authors/arie-cattan/), [Yoav Goldberg](https://md.research.elamur.ai/free/authors/yoav-goldberg/) · **Year:** 2022 · **Venue:** Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2022.aacl-demo.6/) · [PDF](https://aclanthology.org/2022.aacl-demo.6.pdf) · [DOI 10.18653/v1/2022.aacl-demo.6](https://doi.org/10.18653/v1/2022.aacl-demo.6) · [arXiv 2209.04280](https://arxiv.org/abs/2209.04280) · [OpenAlex](https://openalex.org/W4404752353)

**Citations:** 20 citations (openalex-snapshot · 2026-10-14) · [25](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
Coreference resolution groups mentions in a text that point to the same entity. It helps tasks such as information extraction, question answering and summarization, but strong existing tools are hard to use at scale because they need a lot of GPU memory and run slowly. The authors release fastcoref, a pip-installable Python package for English with two models behind one simple API: the accurate LingMess model and a compact model, F-coref.

F-coref is a slimmed-down version of the s2e architecture. It uses DistilRoBERTa instead of Longformer and has much smaller scoring layers. It learns through hard-target distillation: LingMess labels unlabeled Multi-News documents, the student trains on these silver labels, and it is then fine-tuned on OntoNotes. Speed also comes from "leftover batching", which puts full-length segments and document remainders into separate batches to reduce padding.

On a V100, F-coref processes the 2.8K OntoNotes documents in 25 seconds, about 29 times faster than the AllenNLP model, with only a small accuracy loss. This makes coreference practical for large corpora. The package also supports training on new domains or languages.

## Key points
- Compared with the AllenNLP model of Joshi et al. (2020), which needs about 12 minutes and 27GB of GPU memory, F-coref uses roughly 15% of the memory and scores 78.5 vs 79.6 average F1. LingMess reaches 81.4 F1 and runs about twice as fast as AllenNLP.
- The student model shrinks from 494M to 91M parameters and from 26 to 8 layers. Mention pruning is tightened (λ 0.4 → 0.25), which halves pairwise comparisons by a factor of 2.56.
- Standard batching pads 34.7% of OntoNotes tokens at max_length 512. Leftover batching removes much of this and cuts runtime from 35 to 25 seconds.
- Soft (logit-based) distillation failed, reaching only 64 F1 vs 73.7 without distillation. One cause is that the teacher's pairwise logits often violate transitivity.
- Larger unlabeled sets and stronger teachers both help the student: a LingMess teacher gives 78.5 F1, compared with 78.3 for an s2e teacher.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/)

Topics: [Coreference resolution](https://md.research.elamur.ai/free/topics/coreference-resolution/)

## Cited by

Cited by

25 papers of our library cite it (of the 140673 whose bibliographies we read); 6 of them have a page here, 19 not yet.

- [Do Lexical and Contextual Coreference Resolution Systems Degrade Differently under Mention Noise? An Empirical Study on Scientific Software Mentions](https://md.research.elamur.ai/free/papers/alkan-2026-do-lexical-contextual-coreference-resolution/)
- [Lions: 1 and Tigers: 2 and Bears: 3, Oh My! Literary Coreference Annotation with LLMs](https://md.research.elamur.ai/free/papers/hicke-2024-lions-1-tigers-2-bears/)
- [Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends](https://md.research.elamur.ai/free/papers/martinelli-2024-maverick-efficient-accurate-coreference-resolution/)
- [Multilingual Coreference Resolution in Low-resource South Asian Languages](https://md.research.elamur.ai/free/papers/mishra-2024-multilingual-coreference-resolution-low-resource/)
- [CAW-coref: Conjunction-Aware Word-level Coreference Resolution](https://md.research.elamur.ai/free/papers/oosterlinck-2023-caw-coref-conjunction-aware-word/)
- [LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution](https://md.research.elamur.ai/free/papers/otmazgin-2023-lingmess-linguistically-informed-multi-expert/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{otmazgin2022f,
  title = {{F-coref: Fast, Accurate and Easy to Use Coreference Resolution}},
  author = {Otmazgin, Shon and Cattan, Arie and Goldberg, Yoav},
  booktitle = {Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations},
  year = {2022},
  doi = {10.18653/v1/2022.aacl-demo.6},
  eprint = {2209.04280},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2022.aacl-demo.6}
}
```

- [← previous Exploring Length Generalization in Large Language Models](https://md.research.elamur.ai/free/papers/anil-2022-exploring-length-generalization-large-language/)
- [next → Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense Relations](https://md.research.elamur.ai/free/papers/long-2022-facilitating-contrastive-learning-discourse-relational/)
- [↑ back to papers of 2022](https://md.research.elamur.ai/free/papers/2022/)

## References

29 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Geoffrey E. Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the knowledge in a neural network. ArXiv, abs/1503.02531. [↗](https://arxiv.org/abs/1503.02531) [our card](https://md.research.elamur.ai/free/papers/hinton-2015-distilling-knowledge-neural-network/)
2. Jianping Gou, B. Yu, Stephen J. Maybank, and Dacheng Tao. 2021. Knowledge distillation: A survey. ArXiv, abs/2006.05525. [↗](https://arxiv.org/abs/2006.05525)
3. Iz Beltagy, Matthew E. Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. ArXiv, abs/2004.05150. [↗](https://arxiv.org/abs/2004.05150)
4. Sarthak Jain, Madeleine van Zuylen, Hannaneh Hajishirzi, and Iz Beltagy. 2020. SciREX: A challenge dataset for document-level information extraction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7506– 7516, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sarthak+Jain%2C+Madeleine+van+Zuylen%2C+Hannaneh+Hajishirzi%2C+and+Iz+Beltagy%2E+2020%2E+SciREX%3A+A+challenge+dataset+for+document%2Dlevel+information+extraction%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+A)
5. Jifan Chen and Greg Durrett. 2021. Robust question answering through sub-part alignment. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1251–1263, Online. Association for Computational Linguistics. [↗](https://doi.org/10.48448/cbd3-fg58)
6. Xiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen, Linlin Li, Fang Wang, and Qun Liu. 2020. TinyBERT: Distilling BERT for natural language understanding. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4163– 4174, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Xiaoqi+Jiao%2C+Yichun+Yin%2C+Lifeng+Shang%2C+Xin+Jiang%2C+Xiao+Chen%2C+Linlin+Li%2C+Fang+Wang%2C+and+Qun+Liu%2E+2020%2E+TinyBERT%3A+Distilling+BERT+for+natural+language+understanding%2E+In+Findings+of+the+Association+for+C)
7. Janara Christensen, Mausam, Stephen Soderland, and Oren Etzioni. 2013. Towards coherent multi-document summarization. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1163–1173, Atlanta, Georgia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Janara+Christensen%2C+Mausam%2C+Stephen+Soderland%2C+and+Oren+Etzioni%2E+2013%2E+Towards+coherent+multi%2Ddocument+summarization%2E+In+Proceedings+of+the+2013+Conference+of+the+North+American+Chapter+of+the+Associa)
8. Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, and Omer Levy. 2020. Span-BERT: Improving pre-training by representing and predicting spans. Transactions of the Association for Computational Linguistics, 8:64–77. [find](https://scholar.google.com/scholar?q=Mandar+Joshi%2C+Danqi+Chen%2C+Yinhan+Liu%2C+Daniel+S%2E+Weld%2C+Luke+Zettlemoyer%2C+and+Omer+Levy%2E+2020%2E+Span%2DBERT%3A+Improving+pre%2Dtraining+by+representing+and+predicting+spans%2E+Transactions+of+the+Association+for) [our card](https://md.research.elamur.ai/free/papers/joshi-2019-spanbert-improving-pre-training-representing/)
9. Pradeep Dasigi, Nelson F. Liu, Ana Marasović, Noah A. Smith, and Matt Gardner. 2019. Quoref: A reading comprehension dataset with questions requiring coreferential reasoning. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5925–5932, Hong Kong, China. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/d19-1606) [our card](https://md.research.elamur.ai/free/papers/dasigi-2019-quoref-reading-comprehension-dataset-questions/)
10. Mandar Joshi, Omer Levy, Luke Zettlemoyer, and Daniel Weld. 2019. BERT for coreference resolution: Baselines and analysis. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5803–5808, Hong Kong, China. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/d19-1588) [our card](https://md.research.elamur.ai/free/papers/joshi-2019-bert-coreference-resolution-baselines-analysis/)
11. Vladimir Dobrovolskii. 2021. Word-level coreference resolution. In Proceedings of the 2021 Conference Ben Kantor and Amir Globerson. 2019. Coreference resolution with entity equalization. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 673–677, Florence, Italy. Association for Computational Linguistics. [↗](https://doi.org/10.48448/3d5h-p136) [our card](https://md.research.elamur.ai/free/papers/dobrovolskii-2021-word-level-coreference-resolution/)
12. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. CoNLL-2012 shared task: Modeling multilingual unrestricted coreference in OntoNotes. In Joint Conference on EMNLP and CoNLL - Shared Task, pages 1–40, Jeju Island, Korea. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sameer+Pradhan%2C+Alessandro+Moschitti%2C+Nianwen+Xue%2C+Olga+Uryupina%2C+and+Yuchen+Zhang%2E+2012%2E+CoNLL%2D2012+shared+task%3A+Modeling+multilingual+unrestricted+coreference+in+OntoNotes%2E+In+Joint+Conference+on+EM) [our card](https://md.research.elamur.ai/free/papers/pradhan-2012-conll-2012-shared-task-modeling/)
13. Lauri Karttunen. 1969. Discourse referents. In International Conference on Computational Linguistics COLING 1969: Preprint No. 70, Sånga Säby, Sweden. [find](https://scholar.google.com/scholar?q=Lauri+Karttunen%2E+1969%2E+Discourse+referents%2E+In+International+Conference+on+Computational+Linguistics+COLING+1969%3A+Preprint+No%2E+70%2C+S%C3%A5nga+S%C3%A4by%2C+Sweden%2E)
14. Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. ArXiv, abs/1910.01108. [↗](https://arxiv.org/abs/1910.01108)
15. Yuval Kirstain, Ori Ram, and Omer Levy. 2021. Coreference resolution without span representations. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 14–19, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2021.acl-short.3) [our card](https://md.research.elamur.ai/free/papers/kirstain-2021-coreference-resolution-without-span-representations/)
16. Dario Stojanovski and Alexander Fraser. 2018. Coreference and coherence in neural machine translation: A study using oracle experiments. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 49–60, Brussels, Belgium. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Dario+Stojanovski+and+Alexander+Fraser%2E+2018%2E+Coreference+and+coherence+in+neural+machine+translation%3A+A+study+using+oracle+experiments%2E+In+Proceedings+of+the+Third+Conference+on+Machine+Translation%3A+) [our card](https://md.research.elamur.ai/free/papers/stojanovski-2018-coreference-coherence-neural-machine-translation/)
17. Kenton Lee, Luheng He, Mike Lewis, and Luke Zettlemoyer. 2017. End-to-end neural coreference resolution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 188–197, Copenhagen, Denmark. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/d17-1018) [our card](https://md.research.elamur.ai/free/papers/lee-2017-end-end-neural-coreference-resolution/)
18. Raghuveer Thirukovalluru, Nicholas Monath, Kumar Shridhar, Manzil Zaheer, Mrinmaya Sachan, and Andrew McCallum. 2021. Scaling within document coreference to long texts. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 3921–3931, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2021.findings-acl.343) [our card](https://md.research.elamur.ai/free/papers/thirukovalluru-2021-scaling-within-document-coreference-long/)
19. Kenton Lee, Luheng He, and Luke Zettlemoyer. 2018. Higher-order coreference resolution with coarse-to-fine inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 687–692, New Orleans, Louisiana. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/n18-2108) [our card](https://md.research.elamur.ai/free/papers/lee-2018-higher-order-coreference-resolution-coarse/)
20. Shubham Toshniwal, Sam Wiseman, Allyson Ettinger, Karen Livescu, and Kevin Gimpel. 2020. Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8519–8526, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2020.emnlp-main.685) [our card](https://md.research.elamur.ai/free/papers/toshniwal-2020-learning-ignore-long-document-coreference/)
21. Manling Li, Alireza Zareian, Ying Lin, Xiaoman Pan, Spencer Whitehead, Brian Chen, Bo Wu, Heng Ji, Shih-Fu Chang, Clare Voss, Daniel Napierski, and Marjorie Freedman. 2020. GAIA: A fine-grained multimedia knowledge extraction system. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 77–86, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Manling+Li%2C+Alireza+Zareian%2C+Ying+Lin%2C+Xiaoman+Pan%2C+Spencer+Whitehead%2C+Brian+Chen%2C+Bo+Wu%2C+Heng+Ji%2C+Shih%2DFu+Chang%2C+Clare+Voss%2C+Daniel+Napierski%2C+and+Marjorie+Freedman%2E+2020%2E+GAIA%3A+A+fine%2Dgrained+multim)
22. Elena Voita, Pavel Serdyukov, Rico Sennrich, and Ivan Titov. 2018. Context-aware neural machine translation learns anaphora resolution. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1264–1274, Melbourne, Australia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Elena+Voita%2C+Pavel+Serdyukov%2C+Rico+Sennrich%2C+and+Ivan+Titov%2E+2018%2E+Context%2Daware+neural+machine+translation+learns+anaphora+resolution%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Association+for) [our card](https://md.research.elamur.ai/free/papers/voita-2018-context-aware-neural-machine-translation/)
23. Yi Luan, Luheng He, Mari Ostendorf, and Hannaneh Hajishirzi. 2018. Multi-task identification of entities, relations, and coreference for scientific knowledge graph construction. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3219–3232, Brussels, Belgium. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yi+Luan%2C+Luheng+He%2C+Mari+Ostendorf%2C+and+Hannaneh+Hajishirzi%2E+2018%2E+Multi%2Dtask+identification+of+entities%2C+relations%2C+and+coreference+for+scientific+knowledge+graph+construction%2E+In+Proceedings+of+the+) [our card](https://md.research.elamur.ai/free/papers/luan-2018-multi-task-identification-entities-relations/)
24. Kellie Webster, Marta Recasens, Vera Axelrod, and Jason Baldridge. 2018. Mind the GAP: A balanced corpus of gendered ambiguous pronouns. Transactions of the Association for Computational Linguistics, 6:605–617. [↗](https://doi.org/10.1162/tacl_a_00240) [our card](https://md.research.elamur.ai/free/papers/webster-2018-mind-gap-balanced-corpus-gendered/)
25. Wei Wu, Fei Wang, Arianna Yuan, Fei Wu, and Jiwei Li. 2020. CorefQA: Coreference resolution as query-based span prediction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6953–6963, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2020.acl-main.622) [our card](https://md.research.elamur.ai/free/papers/wu-2020-corefqa-coreference-resolution-as-query/)
26. Shon Otmazgin, Arie Cattan, and Yoav Goldberg. 2022. Lingmess: Linguistically informed multi expert scorers for coreference resolution. ArXiv, abs/2205.12644. [↗](https://arxiv.org/abs/2205.12644) [our card](https://md.research.elamur.ai/free/papers/otmazgin-2023-lingmess-linguistically-informed-multi-expert/)
27. Ramakanth Pasunuru, Mengwen Liu, Mohit Bansal, Sujith Ravi, and Markus Dreyer. 2021. Efficiently summarizing text and graph encodings of multi-document clusters. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4768–4779, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ramakanth+Pasunuru%2C+Mengwen+Liu%2C+Mohit+Bansal%2C+Sujith+Ravi%2C+and+Markus+Dreyer%2E+2021%2E+Efficiently+summarizing+text+and+graph+encodings+of+multi%2Ddocument+clusters%2E+In+Proceedings+of+the+2021+Conference+)
28. Patrick Xia, João Sedoc, and Benjamin Van Durme. 2020. Incremental neural coreference resolution in constant memory. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8617–8624, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2020.emnlp-main.695) [our card](https://md.research.elamur.ai/free/papers/xia-2020-incremental-neural-coreference-resolution-constant/)
29. Liyan Xu and Jinho D. Choi. 2020. Revealing the myth of higher-order inference in coreference resolution. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8527–8533, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2020.emnlp-main.686) [our card](https://md.research.elamur.ai/free/papers/xu-2020-revealing-myth-higher-order-inference/)