--- title: "RelaxCor: A Global Relaxation Labeling — Sapena 2010" description: "The paper presents RelaxCor, the system entered by Sapena, Padró and Turmo in SemEval-2010 Task 1, which covered intra-document coreference resolution in…" authors: ["Emili Sapena", "Lluís Padró", "Jordi Turmo"] year: 2010 venue: "Proceedings of the 5th International Workshop on Semantic Evaluation" source: "https://aclanthology.org/S10-1017/" 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/sapena-2010-relaxcor-global-relaxation-labeling-approach/" --- [Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/sapena-2010-relaxcor-global-relaxation-labeling-approach/) [home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2010](https://md.research.elamur.ai/free/papers/2010/) / RelaxCor: A Global Relaxation Labeling Approach to Coreference Resolution # RelaxCor: A Global Relaxation Labeling Approach to Coreference Resolution **Authors:** [Emili Sapena](https://md.research.elamur.ai/free/authors/emili-sapena/), [Lluís Padró](https://md.research.elamur.ai/free/authors/lluis-padro/), [Jordi Turmo](https://md.research.elamur.ai/free/authors/jordi-turmo/) · **Year:** 2010 · **Venue:** Proceedings of the 5th International Workshop on Semantic Evaluation · **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/S10-1017/) · [PDF](https://aclanthology.org/S10-1017.pdf) · [OpenAlex](https://openalex.org/W1721507735) **Citations:** 17 citations (openalex-snapshot · 2026-10-14) · [8](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary The paper presents RelaxCor, the system entered by Sapena, Padró and Turmo in SemEval-2010 Task 1, which covered intra-document coreference resolution in several languages. The system treats coreference as graph partitioning. Mentions become vertices, and edges between mention pairs carry weights built from learned constraints. To obtain these constraints, the authors train C4.5 decision trees on pairwise feature vectors and convert them into rules. Separate models are built for pronoun, named-entity and nominal anaphors. Each rule's weight reflects how often the pairs it covers actually corefer. A relaxation labeling algorithm then iteratively assigns each mention to a partition, considering all mentions jointly. This keeps decisions consistent and enforces transitivity. RelaxCor took part only in the gold-mention setting, for Catalan, Spanish and English. It used no external resources apart from WordNet in the English-open run. The global formulation yields very high precision, which gives strong CEAF and B³ scores, but low recall hurts MUC. Even so, it achieved several of the best results in the task, showing that one language-independent method can be competitive across languages. ## Key points - Constraint weights are calculated as the fraction of coreferent training pairs a rule covers, minus 0.5, so weights can be negative. In the graph, a mention with index i can only take one of the first i partition labels. - Negative pairs made up roughly 94% of the training examples. To make learning feasible, negatives were kept only if they differed from some positive example in at most d = 3 features. - Test CEAF F1 was 70.5 for Catalan, 66.6 for Spanish, 75.6 for English-closed and 75.8 for English-open. B³ F1 was 79.9, 78.2, 84.5 and 84.6, while MUC F1 stayed low, ranging from 24.7 to 42.5. - RelaxCor ranked best on Catalan (CEAF, B³), English-closed (CEAF, B³), English-open (B³) and Spanish (B³). It had the highest precision in nearly all metric and language combinations. - Adding WordNet for English gave only slight, non-significant gains. The authors identify missing semantic and world knowledge, especially for nominal mentions, as the main limit on recall. *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); 3 of them have a page here, 5 not yet. - [Latent Trees for Coreference Resolution](https://md.research.elamur.ai/free/papers/fernandes-2014-latent-trees-coreference-resolution/) - [RelaxCor Participation in CoNLL Shared Task on Coreference Resolution](https://md.research.elamur.ai/free/papers/sapena-2011-relaxcor-participation-conll-shared-task/) - [A Constraint-Based Hypergraph Partitioning Approach to Coreference Resolution](https://md.research.elamur.ai/free/papers/sapena-2013-constraint-based-hypergraph-partitioning-approach/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{sapena2010relaxcor, title = {{RelaxCor: A Global Relaxation Labeling Approach to Coreference Resolution}}, author = {Sapena, Emili and Padró, Lluís and Turmo, Jordi}, booktitle = {Proceedings of the 5th International Workshop on Semantic Evaluation}, year = {2010}, url = {https://aclanthology.org/S10-1017/} } ``` - [← previous Realization of Discourse Relations by Other Means: Alternative Lexicalizations](https://md.research.elamur.ai/free/papers/prasad-2010-realization-discourse-relations-other-means/) - [next → Resolving Object and Attribute Coreference in Opinion Mining](https://md.research.elamur.ai/free/papers/ding-2010-resolving-object-attribute-coreference-opinion/) - [↑ back to papers of 2010](https://md.research.elamur.ai/free/papers/2010/) ## References 6 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. R. A. Hummel and S. W. Zucker. 1987. On the foundations of relaxation labeling processes. pages 585–605. [find](https://scholar.google.com/scholar?q=R%2E+A%2E+Hummel+and+S%2E+W%2E+Zucker%2E+1987%2E+On+the+foundations+of+relaxation+labeling+processes%2E+pages+585%E2%80%93605%2E) 2. G.A. Miller. 1995. WordNet: a lexical database for English. [find](https://scholar.google.com/scholar?q=G%2EA%2E+Miller%2E+1995%2E+WordNet%3A+a+lexical+database+for+English%2E) [our card](https://md.research.elamur.ai/free/papers/lex-1994-miller-wordnet/) 3. J.R. Quinlan. 1993. C4.5: Programs for Machine Learning. Morgan Kaufmann. [find](https://scholar.google.com/scholar?q=J%2ER%2E+Quinlan%2E+1993%2E+C4%2E5%3A+Programs+for+Machine+Learning%2E+Morgan+Kaufmann%2E) [our card](https://md.research.elamur.ai/free/papers/quinlan-1993-c45-programs-machine-learning/) 4. M. Recasens, L. Màrquez, E. Sapena, M.A. Martı́, M. Taulé, V. Hoste, M. Poesio, and Y. Versley. 2010. SemEval-2010 Task 1: Coreference resolution in multiple languages. In Proceedings of the 5th International Workshop on Semantic Evaluations (SemEval-2010), Uppsala, Sweden. [find](https://scholar.google.com/scholar?q=M%2E+Recasens%2C+L%2E+Ma%CC%80rquez%2C+E%2E+Sapena%2C+M%2EA%2E+Mart%C4%B1%CC%81%2C+M%2E+Taule%CC%81%2C+V%2E+Hoste%2C+M%2E+Poesio%2C+and+Y%2E+Versley%2E+2010%2E+SemEval%2D2010+Task+1%3A+Coreference+resolution+in+multiple+languages%2E+In+Proceedings+of+the+5th+Int) [our card](https://md.research.elamur.ai/free/papers/recasens-2009-semeval-2010-task-1-coreference/) 5. E. Sapena, L. Padró, and J. Turmo. 2010. A Global Relaxation Labeling Approach to Coreference Resolution. Submitted. [find](https://scholar.google.com/scholar?q=E%2E+Sapena%2C+L%2E+Padro%CC%81%2C+and+J%2E+Turmo%2E+2010%2E+A+Global+Relaxation+Labeling+Approach+to+Coreference+Resolution%2E+Submitted%2E) [our card](https://md.research.elamur.ai/free/papers/sapena-2010-global-relaxation-labeling-approach-coreference/) 6. W.M. Soon, H.T. Ng, and D.C.Y. Lim. 2001. A Machine Learning Approach to Coreference Resolution of Noun Phrases. Computational Linguistics, 27(4):521–544. [find](https://scholar.google.com/scholar?q=W%2EM%2E+Soon%2C+H%2ET%2E+Ng%2C+and+D%2EC%2EY%2E+Lim%2E+2001%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/)