---
title: "A High-Performance Coreference Resolution System — Zhou 2004"
description: "The paper tackles coreference resolution for general noun phrases in unrestricted English text."
authors: ["GuoDong Zhou", "Jian Su"]
year: 2004
venue: "COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics"
source: "https://aclanthology.org/C04-1075/"
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/zhou-2004-high-performance-coreference-resolution-system/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/zhou-2004-high-performance-coreference-resolution-system/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2004](https://md.research.elamur.ai/free/papers/2004/) / A High-Performance Coreference Resolution System using a Constraint-based Multi-Agent Strategy

# A High-Performance Coreference Resolution System using a Constraint-based Multi-Agent Strategy

**Authors:** [GuoDong Zhou](https://md.research.elamur.ai/free/authors/guodong-zhou/), [Jian Su](https://md.research.elamur.ai/free/authors/jian-su/) · **Year:** 2004 · **Venue:** COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics · **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/C04-1075/) · [PDF](https://aclanthology.org/C04-1075.pdf) · [OpenAlex](https://openalex.org/W2048846610)

**Citations:** 21 citations (openalex-snapshot · 2026-10-14) · [6](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
The paper tackles coreference resolution for general noun phrases in unrestricted English text. It uses the MUC-6 and MUC-7 coreference tasks with their official corpora and scorers. Referring expressions are extracted by a pipeline that shares one HMM-based engine with error-driven learning for named entity recognition, POS tagging and NP chunking.

Resolution then runs in three stages of cooperating agents:
- A common constraint agent removes candidates that clash in gender, number or semantics.
- An agent specific to the anaphor's type (name alias, apposition, pronoun, definite NP, etc.) discards further candidates.
- A preference agent selects the remaining candidate based on proximity.

The key idea is that the closest antecedent in a chain is often linked only indirectly and carries little information. The system therefore looks for the most direct, informative antecedent rather than simply the nearest one.

The approach outperforms the strongest earlier machine-learning systems, mostly through large precision gains at comparable recall. This shows that a simple, knowledge-driven filtering design can compete with learned models.

## Key points
- Results: MUC-6 P/R/F = 84.7 / 65.8 / 73.9; MUC-7 P/R/F = 82.8 / 55.7 / 66.5.
- Compared with Ng and Cardie 2002 (C4.5 and RIPPER variants), F-measure improves by 3.1–4.8 points and precision by 6.7–10.0 points.
- Data: 30 annotated documents per corpus were used for training (about 12,400 words for MUC-6 and 19,000 for MUC-7). Testing used 30 MUC-6 and 20 MUC-7 standard test documents.
- Seven coreference types are defined by anaphor type, each restricting which antecedent types are allowed. For example, definite, demonstrative and bare NPs cannot take pronoun antecedents.
- Limitations: the predicate nominal agent was unfinished, and cataphora and metonymy are not handled. The weakest areas are pronoun and definite NP resolution.

*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

6 papers of our library cite it (of the 140673 whose bibliographies we read); 3 of them have a page here, 3 not yet.

- [Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules](https://md.research.elamur.ai/free/papers/lee-2013-deterministic-coreference-resolution-based-entity/)
- [LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution](https://md.research.elamur.ai/free/papers/otmazgin-2023-lingmess-linguistically-informed-multi-expert/)
- [Easy-first Coreference Resolution](https://md.research.elamur.ai/free/papers/stoyanov-2012-easy-first-coreference-resolution/)

## Cite

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

```bibtex
@inproceedings{zhou2004high,
  title = {{A High-Performance Coreference Resolution System using a Constraint-based Multi-Agent Strategy}},
  author = {Zhou, GuoDong and Su, Jian},
  booktitle = {COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics},
  year = {2004},
  doi = {10.3115/1220355.1220430},
  url = {https://doi.org/10.3115/1220355.1220430}
}
```

- [← previous A General-Purpose, Off-the-shelf Anaphora Resolution Module: Implementation and Preliminary Evaluation](https://md.research.elamur.ai/free/papers/poesio-2004-general-purpose-off-shelf-anaphora/)
- [next → A Labelled Corpus for Prepositional Phrase Attachment](https://md.research.elamur.ai/free/papers/lingbulk-2004-mitchell-labelled-corpus-prepositional-phrase-attachment/)
- [↑ back to papers of 2004](https://md.research.elamur.ai/free/papers/2004/)

## References

18 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Brennan S. E. Friedman M. W. and Pollard C. J. 1987. A centering approach to pronouns. Proceedings of the 25 th Annual Meeting of the Association for Computational Linguistics (ACL’1987), pages 155-162. [find](https://scholar.google.com/scholar?q=Brennan+S%2E+E%2E+Friedman+M%2E+W%2E+and+Pollard+C%2E+J%2E+1987%2E+A+centering+approach+to+pronouns%2E+Proceedings+of+the+25+th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28ACL%E2%80%991987%29%2C+pages+155%2D16)
2. Carbonell J. and Brown R. 1988. Anaphora resolution: a multi-strategy approach. Proceedings of the 12 th International Conference on Computational Linguistics (COLING’1988), pages 96-101, Budapest, Hungary. [find](https://scholar.google.com/scholar?q=Carbonell+J%2E+and+Brown+R%2E+1988%2E+Anaphora+resolution%3A+a+multi%2Dstrategy+approach%2E+Proceedings+of+the+12+th+International+Conference+on+Computational+Linguistics+%28COLING%E2%80%991988%29%2C+pages+96%2D101%2C+Budapest%2C+Hu) [our card](https://md.research.elamur.ai/free/papers/carbonell-1988-anaphora-resolution-multi-strategy-approach/)
3. Carter D. M. 1987. Interpreting Anaphors in Natural Language Texts. Ellis Horwood, Chichester, UK. [find](https://scholar.google.com/scholar?q=Carter+D%2E+M%2E+1987%2E+Interpreting+Anaphors+in+Natural+Language+Texts%2E+Ellis+Horwood%2C+Chichester%2C+UK%2E)
4. Cohen W. 1995. Fast effective rule induction. Proceedings of the Twelfth International Conference on Machine Learning (ICML’1995). pages 115-123. Tahoe City, CA. [find](https://scholar.google.com/scholar?q=Cohen+W%2E+1995%2E+Fast+effective+rule+induction%2E+Proceedings+of+the+Twelfth+International+Conference+on+Machine+Learning+%28ICML%E2%80%991995%29%2E+pages+115%2D123%2E+Tahoe+City%2C+CA%2E)
5. Dagan I. and Itai A. 1990. Automatic processing of large corpora for the resolution of anaphora references. Proceedings of the 13 th International Conference on Computational Linguistics (COLING’1990), pages 1-3, Helsinki, Finland. [find](https://scholar.google.com/scholar?q=Dagan+I%2E+and+Itai+A%2E+1990%2E+Automatic+processing+of+large+corpora+for+the+resolution+of+anaphora+references%2E+Proceedings+of+the+13+th+International+Conference+on+Computational+Linguistics+%28COLING%E2%80%991990%29) [our card](https://md.research.elamur.ai/free/papers/dagan-1990-automatic-processing-large-corpora-resolution/)
6. Grosz B. J. and Sidner C. L. 1986. Attention, intentions and the structure of discourse. Computational Linguistics, 12(3):175-204. [find](https://scholar.google.com/scholar?q=Grosz+B%2E+J%2E+and+Sidner+C%2E+L%2E+1986%2E+Attention%2C+intentions+and+the+structure+of+discourse%2E+Computational+Linguistics%2C+12%283%29%3A175%2D204%2E) [our card](https://md.research.elamur.ai/free/papers/grosz-1986-attention-intentions-structure-discourse/)
7. Lappin S. and Leass H. 1994. An algorithm for pronominal anaphora resolution. Computational Linguistics. 20(4):535-561. [find](https://scholar.google.com/scholar?q=Lappin+S%2E+and+Leass+H%2E+1994%2E+An+algorithm+for+pronominal+anaphora+resolution%2E+Computational+Linguistics%2E+20%284%29%3A535%2D561%2E) [our card](https://md.research.elamur.ai/free/papers/lappin-1994-algorithm-pronominal-anaphora-resolution/)
8. Miller G.A. 1990. WordNet: An online lexical database. International Journal of Lexicography. 3(4):235-312. [find](https://scholar.google.com/scholar?q=Miller+G%2EA%2E+1990%2E+WordNet%3A+An+online+lexical+database%2E+International+Journal+of+Lexicography%2E+3%284%29%3A235%2D312%2E)
9. Mitkov R. 1998. Robust pronoun resolution with limited knowledge. Proceedings of the 36 th Annual Meeting for Computational Linguistics and the 17 th International Conference on Computational Linguistics (COLING/ACL’1998), pages 869-875, Montreal, Canada. [find](https://scholar.google.com/scholar?q=Mitkov+R%2E+1998%2E+Robust+pronoun+resolution+with+limited+knowledge%2E+Proceedings+of+the+36+th+Annual+Meeting+for+Computational+Linguistics+and+the+17+th+International+Conference+on+Computational+Linguist) [our card](https://md.research.elamur.ai/free/papers/mitkov-1998-robust-pronoun-resolution-limited-knowledge/)
10. MUC-6. 1995. Proceedings of the 6 th Message Understanding Conference (MUC-6). Morgan Kaufmann, San Francisco, CA. [find](https://scholar.google.com/scholar?q=MUC%2D6%2E+1995%2E+Proceedings+of+the+6+th+Message+Understanding+Conference+%28MUC%2D6%29%2E+Morgan+Kaufmann%2C+San+Francisco%2C+CA%2E)
11. MUC-7. 1998. Proceedings of the 7 th Message Understanding Conference (MUC-7). Morgan Kaufmann, San Mateo, CA. [find](https://scholar.google.com/scholar?q=MUC%2D7%2E+1998%2E+Proceedings+of+the+7+th+Message+Understanding+Conference+%28MUC%2D7%29%2E+Morgan+Kaufmann%2C+San+Mateo%2C+CA%2E)
12. Ng V. and Cardie C. 2002. Improving machine learning approaches to coreference resolution. Proceedings of the 40 th Annual Meeting of the Association for Computational Linguistics (ACL’2002), pages 104-111, Philadelphia, Penn. [find](https://scholar.google.com/scholar?q=Ng+V%2E+and+Cardie+C%2E+2002%2E+Improving+machine+learning+approaches+to+coreference+resolution%2E+Proceedings+of+the+40+th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28ACL%E2%80%992002%29%2C+pages+10) [our card](https://md.research.elamur.ai/free/papers/ng-2002-improving-machine-learning-approaches-coreference/)
13. Rich E. and LuperFoy S. 1988. An architecture for anaphora resolution. Proceedings of the 2 nd Conference on Applied Natural Language Processing (ANLP’1988), pages 18-24, Austin, TX. [find](https://scholar.google.com/scholar?q=Rich+E%2E+and+LuperFoy+S%2E+1988%2E+An+architecture+for+anaphora+resolution%2E+Proceedings+of+the+2+nd+Conference+on+Applied+Natural+Language+Processing+%28ANLP%E2%80%991988%29%2C+pages+18%2D24%2C+Austin%2C+TX%2E) [our card](https://md.research.elamur.ai/free/papers/rich-1988-architecture-anaphora-resolution/)
14. Soon W. M.., Ng H. T. and Lim C. Y. 2001. A machine learning approach to coreference resolution of noun phrases. Computational Linguistics, 27(4):521-544. [find](https://scholar.google.com/scholar?q=Soon+W%2E+M%2E%2E%2C+Ng+H%2E+T%2E+and+Lim+C%2E+Y%2E+2001%2E+A+machine+learning+approach+to+coreference+resolution+of+noun+phrases%2E+Computational+Linguistics%2C+27%284%29%3A521%2D544%2E) [our card](https://md.research.elamur.ai/free/papers/soon-2001-machine-learning-approach-coreference-resolution/)
15. Strube M. 1998. Never look back: An alternative to centering. Proceedings of the 36 th Annual Meeting of the Association for Computational Linguistics and the 17 th International Conference on Computational Linguistics, pages 1251-1257. [find](https://scholar.google.com/scholar?q=Strube+M%2E+1998%2E+Never+look+back%3A+An+alternative+to+centering%2E+Proceedings+of+the+36+th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+and+the+17+th+International+Conference+on+Computa)
16. Tetreault J. R. 2001. A corpus-based evaluation of centering and pronoun resolution. Computation Linguistics, 27(4):507-520. [find](https://scholar.google.com/scholar?q=Tetreault+J%2E+R%2E+2001%2E+A+corpus%2Dbased+evaluation+of+centering+and+pronoun+resolution%2E+Computation+Linguistics%2C+27%284%29%3A507%2D520%2E) [our card](https://md.research.elamur.ai/free/papers/tetreault-2001-corpus-based-evaluation-centering-pronoun/)
17. Zhou G. D. and Su Jian, 2000. Error-driven HMM-based chunk tagger with context-dependent lexicon. Proceedings of the Joint Conference on Empirical Methods on Natural Language Processing and Very Large Corpus (EMNLP/ VLC'2000). Hong Kong. [find](https://scholar.google.com/scholar?q=Zhou+G%2E+D%2E+and+Su+Jian%2C+2000%2E+Error%2Ddriven+HMM%2Dbased+chunk+tagger+with+context%2Ddependent+lexicon%2E+Proceedings+of+the+Joint+Conference+on+Empirical+Methods+on+Natural+Language+Processing+and+Very+Large)
18. Zhou G. D. and Su Jian. 2002. Named Entity Recognition Using a HMM-based Chunk Tagger, Proceedings of the 40 th Annual Meeting of the Association for Computational Linguistics (ACL’2002). Philadelphia. [find](https://scholar.google.com/scholar?q=Zhou+G%2E+D%2E+and+Su+Jian%2E+2002%2E+Named+Entity+Recognition+Using+a+HMM%2Dbased+Chunk+Tagger%2C+Proceedings+of+the+40+th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28ACL%E2%80%992002%29%2E+Philadelphia)