--- title: "A Joint Framework for Coreference Resolution and — Peng 2015" description: "Coreference systems lose much of their accuracy when they must find mentions in raw text rather than receive gold-annotated ones." authors: ["Haoruo Peng", "Kai-Wei Chang", "Dan Roth"] year: 2015 venue: "Proceedings of the Nineteenth Conference on Computational Natural Language Learning" source: "https://aclanthology.org/K15-1002/" doi: "10.18653/v1/k15-1002" 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/peng-2015-joint-framework-coreference-resolution-mention/" --- [Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/peng-2015-joint-framework-coreference-resolution-mention/) [home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2015](https://md.research.elamur.ai/free/papers/2015/) / A Joint Framework for Coreference Resolution and Mention Head Detection # A Joint Framework for Coreference Resolution and Mention Head Detection **Authors:** [Haoruo Peng](https://md.research.elamur.ai/free/authors/haoruo-peng/), [Kai-Wei Chang](https://md.research.elamur.ai/free/authors/kai-wei-chang/), [Dan Roth](https://md.research.elamur.ai/free/authors/dan-roth/) · **Year:** 2015 · **Venue:** Proceedings of the Nineteenth Conference on Computational Natural Language Learning · **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/K15-1002/) · [PDF](https://aclanthology.org/K15-1002.pdf) · [DOI 10.18653/v1/k15-1002](https://doi.org/10.18653/v1/k15-1002) · [OpenAlex](https://openalex.org/W2250738489) **Citations:** 48 citations (openalex-snapshot · 2026-10-14) · [27](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary Coreference systems lose much of their accuracy when they must find mentions in raw text rather than receive gold-annotated ones. This end-to-end setting is the one that matters in practice. Peng, Chang and Roth address this gap by not treating mention detection as a fixed preprocessing stage. Their system works with mention heads, which are shorter, never overlap, and carry most of the information that coreference features use. They first generate high-recall head candidates by combining a statistical component with existing lexical resources. An Integer Linear Program then jointly decides which candidates are real heads and how they link into coreference chains. It learns a head classifier and a left-linking mention-pair scorer at the same time. Full mention spans are recovered only after linking, using a binary classifier. Experiments on ACE-2004 and CoNLL-2012 (OntoNotes-5.0) show large gains in mention detection and the best end-to-end coreference results reported at the time. The work argues for evaluating NLP systems on raw input. ## Key points - Existing systems, including the Illinois, Berkeley and Stanford coreference systems, score more than 10 points lower with predicted mentions than with gold ones. For example, Illinois on CoNLL-12 falls from 77.05 to 60.00. - The joint ILP extends the best-left-link formulation of Chang et al. (2011) with a variable for each head candidate. A link is allowed only if the candidate is accepted, so the model can discard spurious mentions and singletons. This matters for OntoNotes, which drops singleton mentions. - Mention detection improves by roughly 10–15 F1. The end-to-end system (H-Joint-M) reduces mention detection error by 55.36% on ACE-2004 and 35.49% on CoNLL-2012, measured on full mentions. - The gap between coreference on gold and predicted mentions shrinks by over 20%: 26.28% on ACE-2004 and 22.60% on CoNLL-2012. The candidate generator and the joint inference contribute about equally to this reduction. - Because OntoNotes has no head annotations, heads were extracted in ACE style. The software is released through the Illinois CogComp group. *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 27 papers of our library cite it (of the 140673 whose bibliographies we read); 11 of them have a page here, 16 not yet. - [Improving Coreference Resolution by Learning Entity-Level Distributed Representations](https://md.research.elamur.ai/free/papers/clark-2016-improving-coreference-resolution-learning-entity/) - [Richer Event Description: Integrating event coreference with temporal, causal and bridging annotation](https://md.research.elamur.ai/free/papers/gorman-2016-richer-event-description-integrating-event/) - [Conundrums in Entity Coreference Resolution: Making Sense of the State of the Art](https://md.research.elamur.ai/free/papers/lu-2020-conundrums-entity-coreference-resolution-making/) - [Search Space Pruning: A Simple Solution for Better Coreference Resolvers](https://md.research.elamur.ai/free/papers/moosavi-2016-search-space-pruning-simple-solution/) - [Which Coreference Evaluation Metric Do You Trust? A Proposal for a Link-based Entity Aware Metric](https://md.research.elamur.ai/free/papers/moosavi-2016-which-coreference-evaluation-metric-do/) - [Using Automatically Extracted Minimum Spans to Disentangle Coreference Evaluation from Boundary Detection](https://md.research.elamur.ai/free/papers/moosavi-2019-automatically-extracted-minimum-spans-disentangle/) - [GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue](https://md.research.elamur.ai/free/papers/quan-2019-gecor-end-end-generative-ellipsis/) - [Revisiting the Evaluation for Cross Document Event Coreference](https://md.research.elamur.ai/free/papers/upadhyay-2016-revisiting-evaluation-cross-document-event/) - [ARRAU: Linguistically-Motivated Annotation of Anaphoric Descriptions](https://md.research.elamur.ai/free/papers/uryupina-2016-arrau-linguistically-motivated-annotation-anaphoric/) - [Learning Global Features for Coreference Resolution](https://md.research.elamur.ai/free/papers/wiseman-2016-learning-global-features-coreference-resolution/) - [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://md.research.elamur.ai/free/papers/zhao-2018-gender-bias-coreference-resolution-evaluation/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{peng2015joint, title = {{A Joint Framework for Coreference Resolution and Mention Head Detection}}, author = {Peng, Haoruo and Chang, Kai-Wei and Roth, Dan}, booktitle = {Proceedings of the Nineteenth Conference on Computational Natural Language Learning}, year = {2015}, doi = {10.18653/v1/k15-1002}, url = {https://doi.org/10.18653/v1/k15-1002} } ``` - [← previous A Hierarchy with, of, and for Preposition Supersenses](https://md.research.elamur.ai/free/papers/aclbulk-2015-schneider-hierarchy-preposition-supersenses/) - [next → A Neural Conversational Model](https://md.research.elamur.ai/free/papers/vinyals-2015-neural-conversational-model/) - [↑ back to papers of 2015](https://md.research.elamur.ai/free/papers/2015/) ## References 35 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. A. Bagga and B. Baldwin. 1998. Algorithms for scoring coreference chains. In In The First International Conference on Language Resources and Evaluation Workshop on Linguistics Coreference. [find](https://scholar.google.com/scholar?q=A%2E+Bagga+and+B%2E+Baldwin%2E+1998%2E+Algorithms+for+scoring+coreference+chains%2E+In+In+The+First+International+Conference+on+Language+Resources+and+Evaluation+Workshop+on+Linguistics+Coreference%2E) [our card](https://md.research.elamur.ai/free/papers/bagga-1998-algorithms-scoring-coreference-chains/) 2. E. Bengtson and D. Roth. 2008. Understanding the value of features for coreference resolution. In EMNLP. [find](https://scholar.google.com/scholar?q=E%2E+Bengtson+and+D%2E+Roth%2E+2008%2E+Understanding+the+value+of+features+for+coreference+resolution%2E+In+EMNLP%2E) [our card](https://md.research.elamur.ai/free/papers/bengtson-2008-understanding-value-features-coreference-resolution/) 3. A. Björkelund and J Kuhn. 2014. Learning structured Perceptrons for coreference resolution with latent antecedents and non-local features. In ACL. [find](https://scholar.google.com/scholar?q=A%2E+Bjo%CC%88rkelund+and+J+Kuhn%2E+2014%2E+Learning+structured+Perceptrons+for+coreference+resolution+with+latent+antecedents+and+non%2Dlocal+features%2E+In+ACL%2E) [our card](https://md.research.elamur.ai/free/papers/bjorkelund-2014-learning-structured-perceptrons-coreference-resolution/) 4. C. Cardie and D. Pierce. 1998. Error-driven pruning of Treebanks grammars for base noun phrase identification. In Proceedings of ACL-98. [find](https://scholar.google.com/scholar?q=C%2E+Cardie+and+D%2E+Pierce%2E+1998%2E+Error%2Ddriven+pruning+of+Treebanks+grammars+for+base+noun+phrase+identification%2E+In+Proceedings+of+ACL%2D98%2E) 5. K. Chang, R. Samdani, A. Rozovskaya, N. Rizzolo, M. Sammons, and D. Roth. 2011. Inference protocols for coreference resolution. In CoNLL. [find](https://scholar.google.com/scholar?q=K%2E+Chang%2C+R%2E+Samdani%2C+A%2E+Rozovskaya%2C+N%2E+Rizzolo%2C+M%2E+Sammons%2C+and+D%2E+Roth%2E+2011%2E+Inference+protocols+for+coreference+resolution%2E+In+CoNLL%2E) [our card](https://md.research.elamur.ai/free/papers/chang-2011-inference-protocols-coreference-resolution/) 6. K.-W. Chang, R. Samdani, and D. Roth. 2013. A constrained latent variable model for coreference resolution. In EMNLP. [find](https://scholar.google.com/scholar?q=K%2E%2DW%2E+Chang%2C+R%2E+Samdani%2C+and+D%2E+Roth%2E+2013%2E+A+constrained+latent+variable+model+for+coreference+resolution%2E+In+EMNLP%2E) [our card](https://md.research.elamur.ai/free/papers/chang-2013-constrained-latent-variable-model-coreference/) 7. K. Church. 1988. A stochastic parts program and noun phrase parser for unrestricted text. In ANLP. [find](https://scholar.google.com/scholar?q=K%2E+Church%2E+1988%2E+A+stochastic+parts+program+and+noun+phrase+parser+for+unrestricted+text%2E+In+ANLP%2E) 8. M. Collins. 1999. Head-driven Statistical Models for Natural Language Parsing. Ph.D. thesis, Computer Science Department, University of Pennsylvenia. [find](https://scholar.google.com/scholar?q=M%2E+Collins%2E+1999%2E+Head%2Ddriven+Statistical+Models+for+Natural+Language+Parsing%2E+Ph%2ED%2E+thesis%2C+Computer+Science+Department%2C+University+of+Pennsylvenia%2E) 9. D. Connolly, J. Burger, and D. Day. 1997. A machine learning approach to anaphoric reference. In New Methods in Language Processing. [find](https://scholar.google.com/scholar?q=D%2E+Connolly%2C+J%2E+Burger%2C+and+D%2E+Day%2E+1997%2E+A+machine+learning+approach+to+anaphoric+reference%2E+In+New+Methods+in+Language+Processing%2E) 10. A. Culotta, M. Wick, and A. McCallum. 2007. First-order probabilistic models for coreference resolution. In NAACL. [find](https://scholar.google.com/scholar?q=A%2E+Culotta%2C+M%2E+Wick%2C+and+A%2E+McCallum%2E+2007%2E+First%2Dorder+probabilistic+models+for+coreference+resolution%2E+In+NAACL%2E) [our card](https://md.research.elamur.ai/free/papers/culotta-2007-first-order-probabilistic-models-coreference/) 11. P. Denis and J. Baldridge. 2007. Joint determination of anaphoricity and coreference resolution using integer programming. In NAACL. [find](https://scholar.google.com/scholar?q=P%2E+Denis+and+J%2E+Baldridge%2E+2007%2E+Joint+determination+of+anaphoricity+and+coreference+resolution+using+integer+programming%2E+In+NAACL%2E) [our card](https://md.research.elamur.ai/free/papers/denis-2007-joint-determination-anaphoricity-coreference-resolution/) 12. G. Durrett and D. Klein. 2013. Easy victories and uphill battles in coreference resolution. In EMNLP. [find](https://scholar.google.com/scholar?q=G%2E+Durrett+and+D%2E+Klein%2E+2013%2E+Easy+victories+and+uphill+battles+in+coreference+resolution%2E+In+EMNLP%2E) [our card](https://md.research.elamur.ai/free/papers/durrett-2013-easy-victories-uphill-battles-coreference/) 13. G. Durrett and D. Klein. 2014. A joint model for entity analysis: Coreference, typing, and linking. [find](https://scholar.google.com/scholar?q=G%2E+Durrett+and+D%2E+Klein%2E+2014%2E+A+joint+model+for+entity+analysis%3A+Coreference%2C+typing%2C+and+linking%2E) [our card](https://md.research.elamur.ai/free/papers/durrett-2014-joint-model-entity-analysis-coreference/) 14. J. Finkel and C. Manning. 2009. Nested named entity recognition. In EMNLP. [find](https://scholar.google.com/scholar?q=J%2E+Finkel+and+C%2E+Manning%2E+2009%2E+Nested+named+entity+recognition%2E+In+EMNLP%2E) 15. J. R. Hobbs. 1978. Resolving pronoun references. Lingua. [find](https://scholar.google.com/scholar?q=J%2E+R%2E+Hobbs%2E+1978%2E+Resolving+pronoun+references%2E+Lingua%2E) [our card](https://md.research.elamur.ai/free/papers/hobbs-1978-resolving-pronoun-references/) 16. E. Hovy, M. Marcus, M. Palmer, L. Ramshaw, and R. Weischedel. 2006. Ontonotes: The 90% solution. In Proceedings of HLT/NAACL. [find](https://scholar.google.com/scholar?q=E%2E+Hovy%2C+M%2E+Marcus%2C+M%2E+Palmer%2C+L%2E+Ramshaw%2C+and+R%2E+Weischedel%2E+2006%2E+Ontonotes%3A+The+90%25+solution%2E+In+Proceedings+of+HLT%2FNAACL%2E) 17. J. Jackson and M. Craven. 1996. Learning sparse perceptrons. Proceedings of the 1996 Advances in Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=J%2E+Jackson+and+M%2E+Craven%2E+1996%2E+Learning+sparse+perceptrons%2E+Proceedings+of+the+1996+Advances+in+Neural+Information+Processing+Systems%2E) 18. S. Lappin and H. Leass. 1994. An algorithm for pronominal anaphora resolution. Computational linguistics. [find](https://scholar.google.com/scholar?q=S%2E+Lappin+and+H%2E+Leass%2E+1994%2E+An+algorithm+for+pronominal+anaphora+resolution%2E+Computational+linguistics%2E) [our card](https://md.research.elamur.ai/free/papers/lappin-1994-algorithm-pronominal-anaphora-resolution/) 19. E. Lassalle and P. Denis. 2015. Joint anaphoricity detection and coreference resolution with constrained latent structures. [find](https://scholar.google.com/scholar?q=E%2E+Lassalle+and+P%2E+Denis%2E+2015%2E+Joint+anaphoricity+detection+and+coreference+resolution+with+constrained+latent+structures%2E) 20. H. Lee, Y. Peirsman, A. Chang, N. Chambers, M. Surdeanu, and D. Jurafsky. 2011. Stanford’s multi-pass sieve coreference resolution system at the conll-2011 shared task. In Proceedings of the CoNLL-2011 Shared Task. [find](https://scholar.google.com/scholar?q=H%2E+Lee%2C+Y%2E+Peirsman%2C+A%2E+Chang%2C+N%2E+Chambers%2C+M%2E+Surdeanu%2C+and+D%2E+Jurafsky%2E+2011%2E+Stanford%E2%80%99s+multi%2Dpass+sieve+coreference+resolution+system+at+the+conll%2D2011+shared+task%2E+In+Proceedings+of+the+CoNLL%2D201) [our card](https://md.research.elamur.ai/free/papers/lee-2011-stanford-s-multi-pass-sieve/) 21. H. Lee, M. Recasens, A. Chang, M. Surdeanu, and D. Jurafsky. 2012. Joint entity and event coreference resolution across documents. In EMNLP. [find](https://scholar.google.com/scholar?q=H%2E+Lee%2C+M%2E+Recasens%2C+A%2E+Chang%2C+M%2E+Surdeanu%2C+and+D%2E+Jurafsky%2E+2012%2E+Joint+entity+and+event+coreference+resolution+across+documents%2E+In+EMNLP%2E) [our card](https://md.research.elamur.ai/free/papers/lee-2012-joint-entity-event-coreference-resolution/) 22. X. Luo. 2005. On coreference resolution performance metrics. In EMNLP. [find](https://scholar.google.com/scholar?q=X%2E+Luo%2E+2005%2E+On+coreference+resolution+performance+metrics%2E+In+EMNLP%2E) [our card](https://md.research.elamur.ai/free/papers/luo-2005-coreference-resolution-performance-metrics/) 23. V. Ng and C. Cardie. 2002. Improving machine learning approaches to coreference resolution. In ACL. [find](https://scholar.google.com/scholar?q=V%2E+Ng+and+C%2E+Cardie%2E+2002%2E+Improving+machine+learning+approaches+to+coreference+resolution%2E+In+ACL%2E) [our card](https://md.research.elamur.ai/free/papers/ng-2002-improving-machine-learning-approaches-coreference/) 24. NIST. 2004. The ACE evaluation plan. [find](https://scholar.google.com/scholar?q=NIST%2E+2004%2E+The+ACE+evaluation+plan%2E) 25. S. Pradhan, A. Moschitti, N. Xue, O. Uryupina, and Y. Zhang. 2012. CoNLL-2012 shared task: Modeling multilingual unrestricted coreference in OntoNotes. In CoNLL. [find](https://scholar.google.com/scholar?q=S%2E+Pradhan%2C+A%2E+Moschitti%2C+N%2E+Xue%2C+O%2E+Uryupina%2C+and+Y%2E+Zhang%2E+2012%2E+CoNLL%2D2012+shared+task%3A+Modeling+multilingual+unrestricted+coreference+in+OntoNotes%2E+In+CoNLL%2E) [our card](https://md.research.elamur.ai/free/papers/pradhan-2012-conll-2012-shared-task-modeling/) 26. V. Punyakanok and D. Roth. 2001. The use of classifiers in sequential inference. In NIPS. [find](https://scholar.google.com/scholar?q=V%2E+Punyakanok+and+D%2E+Roth%2E+2001%2E+The+use+of+classifiers+in+sequential+inference%2E+In+NIPS%2E) 27. L. R. Rabiner. 1989. A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE. [find](https://scholar.google.com/scholar?q=L%2E+R%2E+Rabiner%2E+1989%2E+A+tutorial+on+hidden+Markov+models+and+selected+applications+in+speech+recognition%2E+Proceedings+of+the+IEEE%2E) 28. L. A. Ramshaw and M. P. Marcus. 1995. Text chunking using transformation-based learning. In Proceedings of the Third Annual Workshop on Very Large Corpora. [find](https://scholar.google.com/scholar?q=L%2E+A%2E+Ramshaw+and+M%2E+P%2E+Marcus%2E+1995%2E+Text+chunking+using+transformation%2Dbased+learning%2E+In+Proceedings+of+the+Third+Annual+Workshop+on+Very+Large+Corpora%2E) 29. L. Ratinov and D. Roth. 2009. Design challenges and misconceptions in named entity recognition. In Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL). [find](https://scholar.google.com/scholar?q=L%2E+Ratinov+and+D%2E+Roth%2E+2009%2E+Design+challenges+and+misconceptions+in+named+entity+recognition%2E+In+Proc%2E+of+the+Annual+Conference+on+Computational+Natural+Language+Learning+%28CoNLL%29%2E) [our card](https://md.research.elamur.ai/free/papers/ratinov-2009-design-challenges-misconceptions-named-entity/) 30. M. Recasens, M.-C. de Marneffe, and C. Potts. 2013. The life and death of discourse entities: Identifying singleton mentions. In NAACL. [find](https://scholar.google.com/scholar?q=M%2E+Recasens%2C+M%2E%2DC%2E+de+Marneffe%2C+and+C%2E+Potts%2E+2013%2E+The+life+and+death+of+discourse+entities%3A+Identifying+singleton+mentions%2E+In+NAACL%2E) 31. D. Roth and W. Yih. 2004. A linear programming formulation for global inference in natural language tasks. In Hwee Tou Ng and Ellen Riloff, editors, CoNLL. [find](https://scholar.google.com/scholar?q=D%2E+Roth+and+W%2E+Yih%2E+2004%2E+A+linear+programming+formulation+for+global+inference+in+natural+language+tasks%2E+In+Hwee+Tou+Ng+and+Ellen+Riloff%2C+editors%2C+CoNLL%2E) [our card](https://md.research.elamur.ai/free/papers/roth-2004-linear-programming-formulation-global-inference/) 32. S. Sarawagi and W. Cohen. 2004. Semi-Markov conditional random fields for information extraction. In NIPS. [find](https://scholar.google.com/scholar?q=S%2E+Sarawagi+and+W%2E+Cohen%2E+2004%2E+Semi%2DMarkov+conditional+random+fields+for+information+extraction%2E+In+NIPS%2E) 33. Y. Song, J. Jiang, W.-X. Zhao, S. Li, and H. Wang. 2012. Joint learning for coreference resolution with markov logic. In Proceedings of the 2012 Joint Conference of EMNLP-CoNLL. [find](https://scholar.google.com/scholar?q=Y%2E+Song%2C+J%2E+Jiang%2C+W%2E%2DX%2E+Zhao%2C+S%2E+Li%2C+and+H%2E+Wang%2E+2012%2E+Joint+learning+for+coreference+resolution+with+markov+logic%2E+In+Proceedings+of+the+2012+Joint+Conference+of+EMNLP%2DCoNLL%2E) 34. W. M. Soon, H. T. Ng, and D. C. Y. Lim. 2001. A machine learning approach to coreference resolution of noun phrases. Comput. Linguist. [find](https://scholar.google.com/scholar?q=W%2E+M%2E+Soon%2C+H%2E+T%2E+Ng%2C+and+D%2E+C%2E+Y%2E+Lim%2E+2001%2E+A+machine+learning+approach+to+coreference+resolution+of+noun+phrases%2E+Comput%2E+Linguist%2E) [our card](https://md.research.elamur.ai/free/papers/soon-2001-machine-learning-approach-coreference-resolution/) 35. M. Vilain, J. Burger, J. Aberdeen, D. Connolly, and L. Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the 6th conference on Message understanding. [find](https://scholar.google.com/scholar?q=M%2E+Vilain%2C+J%2E+Burger%2C+J%2E+Aberdeen%2C+D%2E+Connolly%2C+and+L%2E+Hirschman%2E+1995%2E+A+model%2Dtheoretic+coreference+scoring+scheme%2E+In+Proceedings+of+the+6th+conference+on+Message+understanding%2E) [our card](https://md.research.elamur.ai/free/papers/vilain-1995-model-theoretic-coreference-scoring-scheme/)