---
title: "Unrestricted Coreference Resolution via Global — Cai 2011"
description: "The paper describes COPA, a coreference resolver entered in the open setting of the CoNLL-2011 shared task on unrestricted coreference over OntoNotes."
authors: ["Jie Cai", "Éva Mújdricza-Maydt", "Michael Strube"]
year: 2011
venue: "Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task"
source: "https://aclanthology.org/W11-1907/"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/cai-2011-unrestricted-coreference-resolution-global-hypergraph/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/cai-2011-unrestricted-coreference-resolution-global-hypergraph/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2011](https://md.research.elamur.ai/free/papers/2011/) / Unrestricted Coreference Resolution via Global Hypergraph Partitioning

# Unrestricted Coreference Resolution via Global Hypergraph Partitioning

**Authors:** [Jie Cai](https://md.research.elamur.ai/free/authors/jie-cai/), Éva Mújdricza-Maydt, [Michael Strube](https://md.research.elamur.ai/free/authors/michael-strube/) · **Year:** 2011 · **Venue:** Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/W11-1907/) · [PDF](https://aclanthology.org/W11-1907.pdf) · [OpenAlex](https://openalex.org/W2107971545)

**Citations:** 19 citations (openalex-snapshot · 2026-10-14) · [8](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
The paper describes COPA, a coreference resolver entered in the open setting of the CoNLL-2011 shared task on unrestricted coreference over OntoNotes. Most systems first classify mention pairs and then cluster them. COPA instead makes a single global decision. Each document becomes a hypergraph: mentions are vertices, and hyperedges are instances of relational features linking two or more mentions. Each feature type gets a weight equal to the share of its training instances that are actually coreferent. Because no explicit model is trained, the authors used only a random 30% of the training data. A recursive two-way spectral clustering procedure then splits the hypergraph into entity clusters. It does not need the number of clusters in advance, only a stopping threshold tuned on development data. Preprocessing relies on external tools inside the BART toolkit, which is why the system competed in the open track. COPA reached an average score of about 55.7 on the test set. Error analysis points to mention detection, missing event mentions, weak world knowledge and pleonastic *it* as the main weaknesses.

## Key points
- The pipeline is built on BART and the MMAX2 format. It uses the Stanford MaxentTagger, the Stanford NER, the Charniak/Johnson reranking parser and the Yamcha chunker. A custom mention detector takes the largest noun phrase spans.
- There are 20 features in three types:
  - negative features (e.g., gender or number mismatch) block edges entirely;
  - positive features (string match, alias, head match, speaker and pronoun rules) create edges;
  - weak features (speak verbs, subjects, WordNet synonyms) only enrich mentions already in the graph.
- Partitioning uses spectral clustering with the symmetric Laplacian and the recursive R2 partitioner, with a stopping criterion α* = 0.06. Eigensolving costs O(n³) in the number of mentions, which is acceptable at a few hundred mentions per document.
- On the test set, F1 was 57.80 for MUC, 67.66 for B-CUBED, 41.67 for CEAF(E) and 71.62 for BLANC. The Overall score was 55.71, against 55.63 on the 202-file development set.
- Event coreference is not handled because verb phrases are not extracted. Further recall is lost to date mentions, punctuation-related boundary mismatches and missing world knowledge.

*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

8 papers of our library cite it (of the 140673 whose bibliographies we read); 6 of them have a page here, 2 not yet.

- [Latent Trees for Coreference Resolution](https://md.research.elamur.ai/free/papers/fernandes-2014-latent-trees-coreference-resolution/)
- [Error-Driven Analysis of Challenges in Coreference Resolution](https://md.research.elamur.ai/free/papers/kummerfeld-2013-error-driven-analysis-challenges-coreference/)
- [Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules](https://md.research.elamur.ai/free/papers/lee-2013-deterministic-coreference-resolution-based-entity/)
- [Collective Classification for Fine-grained Information Status](https://md.research.elamur.ai/free/papers/markert-2012-collective-classification-fine-grained-information/)
- [Multigraph Clustering for Unsupervised Coreference Resolution](https://md.research.elamur.ai/free/papers/martschat-2013-multigraph-clustering-unsupervised-coreference-resolution/)
- [CoNLL-2012 Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes](https://md.research.elamur.ai/free/papers/pradhan-2012-conll-2012-shared-task-modeling/)

## Cite

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

```bibtex
@inproceedings{cai2011unrestricted,
  title = {{Unrestricted Coreference Resolution via Global Hypergraph Partitioning}},
  author = {Cai, Jie and Mújdricza-Maydt, Éva and Strube, Michael},
  booktitle = {Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task},
  year = {2011},
  url = {https://aclanthology.org/W11-1907/}
}
```

- [← previous Underspecifying and Predicting Voice for Surface Realisation Ranking](https://md.research.elamur.ai/free/papers/zarrie-2011-underspecifying-predicting-voice-surface-realisation/)
- [next → Unsupervised Decomposition of a Document into Authorial Components](https://md.research.elamur.ai/free/papers/aclbulk-2011-koppel-unsupervised-decomposition-document-into-authorial/)
- [↑ back to papers of 2011](https://md.research.elamur.ai/free/papers/2011/)

## References

14 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Sameer Agarwal, Jonwoo Lim, Lihi Zelnik-Manor, Pietro Perona, David Kriegman, and Serge Belongie. 2005. Beyond pairwise clustering. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), volume 2, pages 838–845. [find](https://scholar.google.com/scholar?q=Sameer+Agarwal%2C+Jonwoo+Lim%2C+Lihi+Zelnik%2DManor%2C+Pietro+Perona%2C+David+Kriegman%2C+and+Serge+Belongie%2E+2005%2E+Beyond+pairwise+clustering%2E+In+Proceedings+of+the+IEEE+Computer+Society+Conference+on+Computer+V)
2. Jie Cai and Michael Strube. 2010. End-to-end coreference resolution via hypergraph partitioning. In Proceedings of the 23rd International Conference on Computational Linguistics, Beijing, China, 23–27 August 2010, pages 143–151. [find](https://scholar.google.com/scholar?q=Jie+Cai+and+Michael+Strube%2E+2010%2E+End%2Dto%2Dend+coreference+resolution+via+hypergraph+partitioning%2E+In+Proceedings+of+the+23rd+International+Conference+on+Computational+Linguistics%2C+Beijing%2C+China%2C+23%E2%80%9327) [our card](https://md.research.elamur.ai/free/papers/cai-2010-end-end-coreference-resolution-hypergraph/)
3. Eugene Charniak and Mark Johnson. 2005. Coarse-to-fine n-best parsing and MaxEent discriminative reranking. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics, Ann Arbor, Mich., 25–30 June 2005, pages 173–180. [find](https://scholar.google.com/scholar?q=Eugene+Charniak+and+Mark+Johnson%2E+2005%2E+Coarse%2Dto%2Dfine+n%2Dbest+parsing+and+MaxEent+discriminative+reranking%2E+In+Proceedings+of+the+43rd+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+)
4. Christiane Fellbaum, editor. 1998. WordNet: An Electronic Lexical Database. MIT Press, Cambridge, Mass. [find](https://scholar.google.com/scholar?q=Christiane+Fellbaum%2C+editor%2E+1998%2E+WordNet%3A+An+Electronic+Lexical+Database%2E+MIT+Press%2C+Cambridge%2C+Mass%2E)
5. Jenny Rose Finkel, Trond Grenager, and Christopher Manning. 2005. Incorporating non-local information into information extraction systems by Gibbs sampling. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics, Ann Arbor, Mich., 25–30 June 2005, pages 363–370. [find](https://scholar.google.com/scholar?q=Jenny+Rose+Finkel%2C+Trond+Grenager%2C+and+Christopher+Manning%2E+2005%2E+Incorporating+non%2Dlocal+information+into+information+extraction+systems+by+Gibbs+sampling%2E+In+Proceedings+of+the+43rd+Annual+Meeting+o)
6. Taku Kudoh and Yuji Matsumoto. 2000. Use of Support Vector Machines for chunk identification. In Proceedings of the 4th Conference on Computational Natural Language Learning, Lisbon, Portugal, 13–14 September 2000, pages 142–144. [find](https://scholar.google.com/scholar?q=Taku+Kudoh+and+Yuji+Matsumoto%2E+2000%2E+Use+of+Support+Vector+Machines+for+chunk+identification%2E+In+Proceedings+of+the+4th+Conference+on+Computational+Natural+Language+Learning%2C+Lisbon%2C+Portugal%2C+13%E2%80%9314+S)
7. Christoph Müller and Michael Strube. 2006. Multi-level annotation of linguistic data with MMAX2. In Sabine Braun, Kurt Kohn, and Joybrato Mukherjee, editors, Corpus Technology and Language Pedagogy: New Resources, New Tools, New Methods, pages 197–214. Peter Lang: Frankfurt a.M., Germany. [find](https://scholar.google.com/scholar?q=Christoph+Mu%CC%88ller+and+Michael+Strube%2E+2006%2E+Multi%2Dlevel+annotation+of+linguistic+data+with+MMAX2%2E+In+Sabine+Braun%2C+Kurt+Kohn%2C+and+Joybrato+Mukherjee%2C+editors%2C+Corpus+Technology+and+Language+Pedagogy%3A+)
8. NIST. 2004. The ACE evaluation plan: Evaluation of the recognition of ACE entities, ACE relations and ACE events. [http://www.itl.nist.gov/iad/mig//tests/ace/2004/doc/ace04-evalplan-v7.pdf](http://www.itl.nist.gov/iad/mig//tests/ace/2004/doc/ace04-evalplan-v7.pdf). [↗](http://www.itl.nist.gov/iad/mig//tests/ace/2004/doc/ace04-evalplan-v7.pdf)
9. Sameer Pradhan, Lance Ramshaw, Mitchell Marcus, Martha Palmer, Ralph Weischedel, and Nianwen Xue. 2011. CoNLL-2011 Shared Task: Modeling unrestricted coreference in OntoNotes. In Proceedings of the Shared Task of 15th Conference on Computational Natural Language Learning, Portland, Oreg., 23–24 June… [find](https://scholar.google.com/scholar?q=Sameer+Pradhan%2C+Lance+Ramshaw%2C+Mitchell+Marcus%2C+Martha+Palmer%2C+Ralph+Weischedel%2C+and+Nianwen+Xue%2E+2011%2E+CoNLL%2D2011+Shared+Task%3A+Modeling+unrestricted+coreference+in+OntoNotes%2E+In+Proceedings+of+the+Sh) [our card](https://md.research.elamur.ai/free/papers/pradhan-2011-conll-2011-shared-task-modeling/)
10. Veselin Stoyanov, Nathan Gilbert, Claire Cardie, and Ellen Riloff. 2009. Conundrums in noun phrase coreference resolution: Making sense of the state-of-the-art. In Proceedings of the Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th Internationa… [find](https://scholar.google.com/scholar?q=Veselin+Stoyanov%2C+Nathan+Gilbert%2C+Claire+Cardie%2C+and+Ellen+Riloff%2E+2009%2E+Conundrums+in+noun+phrase+coreference+resolution%3A+Making+sense+of+the+state%2Dof%2Dthe%2Dart%2E+In+Proceedings+of+the+Joint+Conference+) [our card](https://md.research.elamur.ai/free/papers/stoyanov-2009-conundrums-noun-phrase-coreference-resolution/)
11. Kristina Toutanova, Dan Klein, Christopher D. Manning, and Yoram Singer. 2003. Feature-rich part-of-speech tagging with a cyclic dependency network. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Edmonton, Al… [find](https://scholar.google.com/scholar?q=Kristina+Toutanova%2C+Dan+Klein%2C+Christopher+D%2E+Manning%2C+and+Yoram+Singer%2E+2003%2E+Feature%2Drich+part%2Dof%2Dspeech+tagging+with+a+cyclic+dependency+network%2E+In+Proceedings+of+the+Human+Language+Technology+Con)
12. Yannick Versley, Simone Paolo Ponzetto, Massimo Poesio, Vladimir Eidelman, Alan Jern, Jason Smith, Xiaofeng Yang, and Alessandro Moschitti. 2008. BART: A modular toolkit for coreference resolution. In Companion Volume to the Proceedings of the 46th Annual Meeting of the Association for Computational… [find](https://scholar.google.com/scholar?q=Yannick+Versley%2C+Simone+Paolo+Ponzetto%2C+Massimo+Poesio%2C+Vladimir+Eidelman%2C+Alan+Jern%2C+Jason+Smith%2C+Xiaofeng+Yang%2C+and+Alessandro+Moschitti%2E+2008%2E+BART%3A+A+modular+toolkit+for+coreference+resolution%2E+In) [our card](https://md.research.elamur.ai/free/papers/versley-2008-bart-modular-toolkit-coreference-resolution/)
13. Ulrike von Luxburg. 2007. A tutorial on spectral clustering. Statistics and Computing, 17(4):395–416. [find](https://scholar.google.com/scholar?q=Ulrike+von+Luxburg%2E+2007%2E+A+tutorial+on+spectral+clustering%2E+Statistics+and+Computing%2C+17%284%29%3A395%E2%80%93416%2E)
14. Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El-Bachouti, Robert Belvin, and Ann Houston. 2011. OntoNotes release 4.0. LDC2011T03, Philadelphia, Penn.: Linguistic Data Consortium. [find](https://scholar.google.com/scholar?q=Ralph+Weischedel%2C+Martha+Palmer%2C+Mitchell+Marcus%2C+Eduard+Hovy%2C+Sameer+Pradhan%2C+Lance+Ramshaw%2C+Nianwen+Xue%2C+Ann+Taylor%2C+Jeff+Kaufman%2C+Michelle+Franchini%2C+Mohammed+El%2DBachouti%2C+Robert+Belvin%2C+and+Ann+Ho)