---
title: "BART: A Modular Toolkit for Coreference — Versley 2008"
description: "Building a coreference resolver that works end-to-end, from raw text to entity chains, takes substantial engineering."
authors: ["Yannick Versley", "Simone Paolo Ponzetto", "Massimo Poesio", "Vladimir Eidelman", "Alan Jern", "Jason Smith", "Xiaofeng Yang", "Alessandro Moschitti"]
year: 2008
venue: "Proceedings of the ACL-08: HLT Demo Session"
source: "https://aclanthology.org/P08-4003/"
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/versley-2008-bart-modular-toolkit-coreference-resolution/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/versley-2008-bart-modular-toolkit-coreference-resolution/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2008](https://md.research.elamur.ai/free/papers/2008/) / BART: A Modular Toolkit for Coreference Resolution

# BART: A Modular Toolkit for Coreference Resolution

**Authors:** [Yannick Versley](https://md.research.elamur.ai/free/authors/yannick-versley/), [Simone Paolo Ponzetto](https://md.research.elamur.ai/free/authors/simone-paolo-ponzetto/), [Massimo Poesio](https://md.research.elamur.ai/free/authors/massimo-poesio/), Vladimir Eidelman, Alan Jern, Jason Smith, [Xiaofeng Yang](https://md.research.elamur.ai/free/authors/xiaofeng-yang/), [Alessandro Moschitti](https://md.research.elamur.ai/free/authors/alessandro-moschitti/) · **Year:** 2008 · **Venue:** Proceedings of the ACL-08: HLT Demo Session · **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/P08-4003/) · [PDF](https://aclanthology.org/P08-4003.pdf) · [OpenAlex](https://openalex.org/W2401705518)

**Citations:** 137 citations (openalex-snapshot · 2026-10-14) · [61](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
Building a coreference resolver that works end-to-end, from raw text to entity chains, takes substantial engineering. As a result, many researchers either rely on gold mentions or skip coreference altogether. BART is an open-source, highly modular toolkit created at the Johns Hopkins Summer Workshop 2007 to address this. It builds on Ponzetto and Strube (2006) and borrows ideas from GUITAR and other systems.

The toolkit keeps each stage separate:
- **Preprocessing:** pipelines based on chunkers, parsers, or an ACE mention tagger, with output stored in MMAX2 standoff format.
- **Feature extraction:** pairwise feature extractors selected through an XML configuration file.
- **Learning:** wrappers for several machine-learning back ends.
- **Training/testing logic:** a pluggable encoder/decoder component that controls how pairs are sampled and how mentions are clustered.

Simply re-creating the baseline from Soon et al. (2001) is already enough to outperform comparable systems on MUC data. Adding syntactic tree-kernel features and Wikipedia-derived knowledge brings ACE-2 performance close to Ng (2007). BART therefore serves both as a ready-to-use resolver and as a shared platform for coreference research.

## Key points
- With Soon et al.'s features and the built-in maximum entropy learner, BART reaches 65.8% F on MUC6 and 62.9% F on MUC7. It beats JavaRAP on pronouns and Uryupina's (2006) Soon reimplementation.
- On ACE-2, the extended feature set achieves F = 0.630 (BNews), 0.658 (NPaper) and 0.627 (NWire). Ng (2007) reports 0.647, 0.646 and 0.633, but trains on the full ACE training corpus. Pronoun recall with the extended set is 73.4%.
- Three preprocessing pipelines are available:
  - a chunking pipeline (Stanford POS tagger, YamCha, Stanford NER);
  - a parsing pipeline (Charniak–Johnson reranking parser, or the Berkeley parser for a pure-Java setup);
  - the Carafe pipeline with MITRE's ACE mention tagger.
- Supported learners are WEKA, SVMLight/TK (tree-valued features) and a MaxEnt classifier optimized with L-BFGS. Results can be inspected in MMAX2 for error analysis.
- BART is freely available from the University of Tübingen. Groups outside the original team already use it for research.

*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/) · [Part-of-speech tagging](https://md.research.elamur.ai/free/topics/part-of-speech-tagging/)

## Cited by

Cited by

61 papers of our library cite it (of the 140673 whose bibliographies we read); 28 of them have a page here, 33 not yet.

- [Neural Coreference Resolution for Arabic](https://md.research.elamur.ai/free/papers/aloraini-2020-neural-coreference-resolution-arabic/)
- [Domain Adaptation of Coreference Resolution for Radiology Reports](https://md.research.elamur.ai/free/papers/apostolova-2012-domain-adaptation-coreference-resolution-radiology/)
- [BART: A Multilingual Anaphora Resolution System](https://md.research.elamur.ai/free/papers/broscheit-2010-bart-multilingual-anaphora-resolution-system/)
- [Extending BART to Provide a Coreference Resolution System for German](https://md.research.elamur.ai/free/papers/broscheit-2010-extending-bart-provide-coreference-resolution/)
- [End-to-End Coreference Resolution via Hypergraph Partitioning](https://md.research.elamur.ai/free/papers/cai-2010-end-end-coreference-resolution-hypergraph/)
- [Evaluation Metrics For End-to-End Coreference Resolution Systems](https://md.research.elamur.ai/free/papers/cai-2010-evaluation-metrics-end-end-coreference/)
- [Unrestricted Coreference Resolution via Global Hypergraph Partitioning](https://md.research.elamur.ai/free/papers/cai-2011-unrestricted-coreference-resolution-global-hypergraph/)
- [EM Works for Pronoun Anaphora Resolution](https://md.research.elamur.ai/free/papers/charniak-2009-em-works-pronoun-anaphora-resolution/)
- [Poly-co: a multilayer perceptron approach for coreference detection](https://md.research.elamur.ai/free/papers/charton-2011-poly-co-multilayer-perceptron-approach/)
- [A Unified Event Coreference Resolution by Integrating Multiple Resolvers](https://md.research.elamur.ai/free/papers/chen-2011-unified-event-coreference-resolution-integrating/)
- [Easy Victories and Uphill Battles in Coreference Resolution](https://md.research.elamur.ai/free/papers/durrett-2013-easy-victories-uphill-battles-coreference/)
- [Apports des analyses syntaxiques pour la détection automatique de mentions dans un corpus de français oral](https://md.research.elamur.ai/free/papers/grobol-2017-apports-analyses-syntaxiques-detection/)
- [Removing the Training Wheels: A Coreference Dataset that Entertains Humans and Challenges Computers](https://md.research.elamur.ai/free/papers/guha-2015-removing-training-wheels-coreference-dataset/)
- [The Taming of Reconcile as a Biomedical Coreference Resolver](https://md.research.elamur.ai/free/papers/kim-2011-taming-reconcile-as-biomedical-coreference/)
- [SUCRE: A Modular System for Coreference Resolution](https://md.research.elamur.ai/free/papers/kobdani-2010-sucre-modular-system-coreference-resolution/)
- [Creating a Coreference Resolution System for Polish](https://md.research.elamur.ai/free/papers/kopec-2012-creating-coreference-resolution-system-polish/)
- [Error-Driven Analysis of Challenges in Coreference Resolution](https://md.research.elamur.ai/free/papers/kummerfeld-2013-error-driven-analysis-challenges-coreference/)
- [Transferring Coreference Resolvers with Posterior Regularization](https://md.research.elamur.ai/free/papers/martins-2015-transferring-coreference-resolvers-posterior-regularization/)
- [Multigraph Clustering for Unsupervised Coreference Resolution](https://md.research.elamur.ai/free/papers/martschat-2013-multigraph-clustering-unsupervised-coreference-resolution/)
- [Coreference Annotation Scheme and Relation Types for Hindi](https://md.research.elamur.ai/free/papers/mujadia-2016-coreference-annotation-scheme-relation-types/)
- [Supervised Noun Phrase Coreference Research: The First Fifteen Years](https://md.research.elamur.ai/free/papers/ng-2010-supervised-noun-phrase-coreference-research/)
- [Creating a Coreference Resolution System for Italian](https://md.research.elamur.ai/free/papers/poesio-2010-creating-coreference-resolution-system-italian/)
- [Anaphora Resolution with the ARRAU Corpus](https://md.research.elamur.ai/free/papers/poesio-2018-anaphora-resolution-arrau-corpus/)
- [CoNLL-2012 Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes](https://md.research.elamur.ai/free/papers/pradhan-2012-conll-2012-shared-task-modeling/)
- [Resolving Complex Cases of Definite Pronouns: The Winograd Schema Challenge](https://md.research.elamur.ai/free/papers/rahman-2012-resolving-complex-cases-definite-pronouns/)
- [Coreference Resolution with Reconcile](https://md.research.elamur.ai/free/papers/stoyanov-2010-coreference-resolution-reconcile/)
- [Deep Cross-Lingual Coreference Resolution for Less-Resourced Languages: The Case of Basque](https://md.research.elamur.ai/free/papers/urbizu-2019-deep-cross-lingual-coreference-resolution/)
- [Domain-specific vs. Uniform Modeling for Coreference Resolution](https://md.research.elamur.ai/free/papers/uryupina-2012-domain-specific-vs-uniform-modeling/)

## Cite

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

```bibtex
@inproceedings{versley2008bart,
  title = {{BART: A Modular Toolkit for Coreference Resolution}},
  author = {Versley, Yannick and Ponzetto, Simone Paolo and Poesio, Massimo and Eidelman, Vladimir and Jern, Alan and Smith, Jason and Yang, Xiaofeng and Moschitti, Alessandro},
  booktitle = {Proceedings of the ACL-08: HLT Demo Session},
  year = {2008},
  doi = {10.63317/28a2xqhvmavx},
  url = {https://doi.org/10.63317/28a2xqhvmavx}
}
```

- [← previous Automatic induction of FrameNet lexical units](https://md.research.elamur.ai/free/papers/pennacchiotti-2008-automatic-induction-framenet-lexical-units/)
- [next → Classification of Verb-Particle Constructions with the Google Web1T Corpus](https://md.research.elamur.ai/free/papers/aclbulk-2008-kummerfeld-classification-verb-particle-constructions-google/)
- [↑ back to papers of 2008](https://md.research.elamur.ai/free/papers/2008/)

## References

24 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Charniak, E. and Johnson, M. (2005). Coarse-to-fine n-best parsing and maxent discriminative reranking. In Proc. [find](https://scholar.google.com/scholar?q=Charniak%2C+E%2E+and+Johnson%2C+M%2E+%282005%29%2E+Coarse%2Dto%2Dfine+n%2Dbest+parsing+and+maxent+discriminative+reranking%2E+In+Proc%2E) [our card](https://md.research.elamur.ai/free/papers/narrative-2005-charniak-coarse-fine-n-best-parsing/)
2. Culotta, A., Wick, M., and McCallum, A. (2007). First-order probabilistic models for coreference resolution. In Proc. HLT/NAACL 2007. [find](https://scholar.google.com/scholar?q=Culotta%2C+A%2E%2C+Wick%2C+M%2E%2C+and+McCallum%2C+A%2E+%282007%29%2E+First%2Dorder+probabilistic+models+for+coreference+resolution%2E+In+Proc%2E+HLT%2FNAACL+2007%2E) [our card](https://md.research.elamur.ai/free/papers/culotta-2007-first-order-probabilistic-models-coreference/)
3. Denis, P. and Baldridge, J. (2007). A ranking approach to pronoun resolution. In Proc. [find](https://scholar.google.com/scholar?q=Denis%2C+P%2E+and+Baldridge%2C+J%2E+%282007%29%2E+A+ranking+approach+to+pronoun+resolution%2E+In+Proc%2E)
4. Finkel, J. R., Grenager, T., and Manning, C. (2005). Incorporating non-local information into information extraction systems by Gibbs sampling. In Proc. [find](https://scholar.google.com/scholar?q=Finkel%2C+J%2E+R%2E%2C+Grenager%2C+T%2E%2C+and+Manning%2C+C%2E+%282005%29%2E+Incorporating+non%2Dlocal+information+into+information+extraction+systems+by+Gibbs+sampling%2E+In+Proc%2E)
5. Joachims, T. (1999). Making large-scale SVM learning practical. In Schölkopf, B., Burges, C., and Smola, A., editors, Advances in Kernel Methods - Support Vector Learning. [find](https://scholar.google.com/scholar?q=Joachims%2C+T%2E+%281999%29%2E+Making+large%2Dscale+SVM+learning+practical%2E+In+Scho%CC%88lkopf%2C+B%2E%2C+Burges%2C+C%2E%2C+and+Smola%2C+A%2E%2C+editors%2C+Advances+in+Kernel+Methods+%2D+Support+Vector+Learning%2E)
6. NPaper Prec F 0.526 0.586 0.677 0.658 0.797 0.646 NWire Prec 0.474 0.652 0.775 Recl 0.663 0.641 0.544 Recl 0.608 0.604 0.535 F 0.533 0.627 0.633 [find](https://scholar.google.com/scholar?q=NPaper+Prec+F+0%2E526+0%2E586+0%2E677+0%2E658+0%2E797+0%2E646+NWire+Prec+0%2E474+0%2E652+0%2E775+Recl+0%2E663+0%2E641+0%2E544+Recl+0%2E608+0%2E604+0%2E535+F+0%2E533+0%2E627+0%2E633)
7. Kudoh, T. and Matsumoto, Y. (2000). Use of Support Vector Machines for chunk identification. In Proc. [find](https://scholar.google.com/scholar?q=Kudoh%2C+T%2E+and+Matsumoto%2C+Y%2E+%282000%29%2E+Use+of+Support+Vector+Machines+for+chunk+identification%2E+In+Proc%2E)
8. Liu, D. C. and Nocedal, J. (1989). On the limited memory method for large scale optimization. Mathematical Programming B, 45(3):503–528. [find](https://scholar.google.com/scholar?q=Liu%2C+D%2E+C%2E+and+Nocedal%2C+J%2E+%281989%29%2E+On+the+limited+memory+method+for+large+scale+optimization%2E+Mathematical+Programming+B%2C+45%283%29%3A503%E2%80%93528%2E)
9. McCarthy, J. F. and Lehnert, W. G. (1995). Using decision trees for coreference resolution. In Proc. [find](https://scholar.google.com/scholar?q=McCarthy%2C+J%2E+F%2E+and+Lehnert%2C+W%2E+G%2E+%281995%29%2E+Using+decision+trees+for+coreference+resolution%2E+In+Proc%2E)
10. Morton, T. S. (2000). Coreference for NLP applications. In Proc. [find](https://scholar.google.com/scholar?q=Morton%2C+T%2E+S%2E+%282000%29%2E+Coreference+for+NLP+applications%2E+In+Proc%2E)
11. Moschitti, A. (2006). Making tree kernels practical for natural language learning. In Proc. [find](https://scholar.google.com/scholar?q=Moschitti%2C+A%2E+%282006%29%2E+Making+tree+kernels+practical+for+natural+language+learning%2E+In+Proc%2E)
12. Müller, C. and Strube, M. (2006). Multi-level annotation of linguistic data with MMAX2. In Braun, S., Kohn, K., and Mukherjee, J., editors, Corpus Technology and Language Pedagogy: New Resources, New Tools, New Methods. Peter Lang, Frankfurt a.M., Germany. [find](https://scholar.google.com/scholar?q=Mu%CC%88ller%2C+C%2E+and+Strube%2C+M%2E+%282006%29%2E+Multi%2Dlevel+annotation+of+linguistic+data+with+MMAX2%2E+In+Braun%2C+S%2E%2C+Kohn%2C+K%2E%2C+and+Mukherjee%2C+J%2E%2C+editors%2C+Corpus+Technology+and+Language+Pedagogy%3A+New+Resources%2C+New)
13. Ng, V. (2007). Shallow semantics for coreference resolution. In Proc. [find](https://scholar.google.com/scholar?q=Ng%2C+V%2E+%282007%29%2E+Shallow+semantics+for+coreference+resolution%2E+In+Proc%2E)
14. Petrov, S., Barett, L., Thibaux, R., and Klein, D. (2006). Learning accurate, compact, and interpretable tree annotation. In COLING-ACL 2006. [find](https://scholar.google.com/scholar?q=Petrov%2C+S%2E%2C+Barett%2C+L%2E%2C+Thibaux%2C+R%2E%2C+and+Klein%2C+D%2E+%282006%29%2E+Learning+accurate%2C+compact%2C+and+interpretable+tree+annotation%2E+In+COLING%2DACL+2006%2E) [our card](https://md.research.elamur.ai/free/papers/aclbulk-2006-petrov-learning-accurate-compact-interpretable-tree/)
15. Ponzetto, S. P. and Strube, M. (2006). Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution. In Proc. HLT/NAACL 2006. [find](https://scholar.google.com/scholar?q=Ponzetto%2C+S%2E+P%2E+and+Strube%2C+M%2E+%282006%29%2E+Exploiting+semantic+role+labeling%2C+WordNet+and+Wikipedia+for+coreference+resolution%2E+In+Proc%2E+HLT%2FNAACL+2006%2E) [our card](https://md.research.elamur.ai/free/papers/ponzetto-2006-exploiting-semantic-role-labeling-wordnet/)
16. Qiu, L., Kan, M.-Y., and Chua, T.-S. (2004). A public reference implementation of the RAP anaphora resolution algorithm. In Proc. [find](https://scholar.google.com/scholar?q=Qiu%2C+L%2E%2C+Kan%2C+M%2E%2DY%2E%2C+and+Chua%2C+T%2E%2DS%2E+%282004%29%2E+A+public+reference+implementation+of+the+RAP+anaphora+resolution+algorithm%2E+In+Proc%2E) [our card](https://md.research.elamur.ai/free/papers/qiu-2004-public-reference-implementation-rap-anaphora/)
17. Soon, W. M., Ng, H. T., and Lim, D. 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%2C+W%2E+M%2E%2C+Ng%2C+H%2E+T%2E%2C+and+Lim%2C+D%2E+C%2E+Y%2E+%282001%29%2E+A+machine+learning+approach+to+coreference+resolution+of+noun+phrases%2E+Computational+Linguistics%2C+27%284%29%3A521%E2%80%93544%2E) [our card](https://md.research.elamur.ai/free/papers/soon-2001-machine-learning-approach-coreference-resolution/)
18. Steinberger, J., Poesio, M., Kabadjov, M., and Jezek, K. (2007). Two uses of anaphora resolution in summarization. Information Processing and Management, 43:1663–1680. Special issue on Summarization. [find](https://scholar.google.com/scholar?q=Steinberger%2C+J%2E%2C+Poesio%2C+M%2E%2C+Kabadjov%2C+M%2E%2C+and+Jezek%2C+K%2E+%282007%29%2E+Two+uses+of+anaphora+resolution+in+summarization%2E+Information+Processing+and+Management%2C+43%3A1663%E2%80%931680%2E+Special+issue+on+Summarization%2E)
19. Toutanova, K., Klein, D., Manning, C. D., and Singer, Y. (2003). Feature-rich part-of-speech tagging with a cyclic dependency network. In Proc. [find](https://scholar.google.com/scholar?q=Toutanova%2C+K%2E%2C+Klein%2C+D%2E%2C+Manning%2C+C%2E+D%2E%2C+and+Singer%2C+Y%2E+%282003%29%2E+Feature%2Drich+part%2Dof%2Dspeech+tagging+with+a+cyclic+dependency+network%2E+In+Proc%2E)
20. Uryupina, O. (2006). Coreference resolution with and without linguistic knowledge. In Proc. [find](https://scholar.google.com/scholar?q=Uryupina%2C+O%2E+%282006%29%2E+Coreference+resolution+with+and+without+linguistic+knowledge%2E+In+Proc%2E) [our card](https://md.research.elamur.ai/free/papers/uryupina-2006-coreference-resolution-without-linguistic-knowledge/)
21. Versley, Y. (2006). A constraint-based approach to noun phrase coreference resolution in German newspaper text. In Konferenz zur Verarbeitung Natürlicher Sprache (KONVENS 2006). [find](https://scholar.google.com/scholar?q=Versley%2C+Y%2E+%282006%29%2E+A+constraint%2Dbased+approach+to+noun+phrase+coreference+resolution+in+German+newspaper+text%2E+In+Konferenz+zur+Verarbeitung+Natu%CC%88rlicher+Sprache+%28KONVENS+2006%29%2E)
22. Wellner, B. and Vilain, M. (2006). Leveraging machine readable dictionaries in discriminative sequence models. In Proc. [find](https://scholar.google.com/scholar?q=Wellner%2C+B%2E+and+Vilain%2C+M%2E+%282006%29%2E+Leveraging+machine+readable+dictionaries+in+discriminative+sequence+models%2E+In+Proc%2E)
23. Witten, I. and Frank, E. (2005). Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann. [find](https://scholar.google.com/scholar?q=Witten%2C+I%2E+and+Frank%2C+E%2E+%282005%29%2E+Data+Mining%3A+Practical+machine+learning+tools+and+techniques%2E+Morgan+Kaufmann%2E)
24. Yang, X., Su, J., and Tan, C. L. (2006). Kernel-based pronoun resolution with structured syntactic knowledge. In Proc. CoLing/ACL-2006. [find](https://scholar.google.com/scholar?q=Yang%2C+X%2E%2C+Su%2C+J%2E%2C+and+Tan%2C+C%2E+L%2E+%282006%29%2E+Kernel%2Dbased+pronoun+resolution+with+structured+syntactic+knowledge%2E+In+Proc%2E+CoLing%2FACL%2D2006%2E) [our card](https://md.research.elamur.ai/free/papers/yang-2006-kernel-based-pronoun-resolution-structured/)