--- title: "Coreference Resolution Using Semantic — Yang 2007" description: "Coreference systems need to judge whether two noun phrases are semantically compatible." authors: ["Xiaofeng Yang", "Jian Su"] year: 2007 venue: "Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics" source: "https://aclanthology.org/P07-1067/" 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/en/papers/yang-2007-coreference-resolution-semantic-relatedness-information/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yang-2007-coreference-resolution-semantic-relatedness-information/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2007](https://md.research.elamur.ai/free/en/papers/2007/) / Coreference Resolution Using Semantic Relatedness Information from Automatically Discovered Patterns # Coreference Resolution Using Semantic Relatedness Information from Automatically Discovered Patterns **Authors:** [Xiaofeng Yang](https://md.research.elamur.ai/free/en/authors/xiaofeng-yang/), [Jian Su](https://md.research.elamur.ai/free/en/authors/jian-su/) · **Year:** 2007 · **Venue:** Proceedings of the 45th Annual Meeting of the Association of 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/P07-1067/) · [PDF](https://aclanthology.org/P07-1067.pdf) · [OpenAlex](https://openalex.org/W2171682787) **Citations:** 52 citations (openalex-snapshot · 2026-10-14) · [17](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary Coreference systems need to judge whether two noun phrases are semantically compatible. Lexicons such as WordNet lack many proper names and relation types. Earlier corpus-based methods relied on hand-picked templates like Hearst-style "X such as Y", which cover mostly is-a links. Yang and Su learn such templates automatically instead. NP pairs taken from coreference training instances act as positive and negative seeds. For each pair, a large corpus (Wikipedia) is searched for co-occurrences separated by no more than three tokens, and the surrounding context becomes a surface pattern. Patterns are ranked by frequency, filtered frequency or PMI-based reliability. They are then used in one of two ways: as individual top-ranked features, or combined into a single relatedness score (SRel). Both options feed a C5 decision-tree learner in the Soon et al. / Ng and Cardie framework. On ACE data, SRel works best, especially for proper names. It raises recall while keeping precision stable, showing that automatically discovered patterns can supply semantic knowledge that lexicons lack. ## Key points - Evaluated on three ACE domains: NWire, NPaper and BNews. The baseline uses standard features such as string match, name alias, apposition and agreement, and is trained with C5. Training is extended with negative instances built from non-anaphors that the classifier wrongly resolved. - Seed pairs keep only the head word for common nouns and the full string for proper names. Pairs with pronouns or identical heads are skipped. Matched contexts become templates with \<#t1#>/\<#t2#> slots. - Using top-ranked pattern features raised recall by up to 3.3% in NWire. Precision fell by up to 1.2%, and F-measure improved by 1.9% in NWire, with no gain in the other two domains. Applying these features to all NP types, rather than only proper names, lowered precision considerably. - The single SRel feature reached F-measures of 67.1% (NWire), 65.0% (NPaper) and 62.7% (BNews), beating the baseline in every domain. In NWire the gain was a statistically significant 2.1% (t-test, p ≤ 0.05). - In the learned decision trees, pattern features appear near the top, close to name alias and apposition features. Most of the useful patterns are copula constructions such as "\ ) is a \". The authors suggest Web-scale text as future work to address sparse co-occurrences. *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/en/shelves/linguistics/) Topics: [Coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) ## Cited by Cited by 17 papers of our library cite it (of the 140673 whose bibliographies we read); 8 of them have a page here, 9 not yet. - [Coreference Semantics from Web Features](https://md.research.elamur.ai/free/en/papers/bansal-2012-coreference-semantics-web-features/) - [Resolving Object and Attribute Coreference in Opinion Mining](https://md.research.elamur.ai/free/en/papers/ding-2010-resolving-object-attribute-coreference-opinion/) - [Employing the Centering Theory in Pronoun Resolution from the Semantic Perspective](https://md.research.elamur.ai/free/en/papers/kong-2009-employing-centering-theory-pronoun-resolution/) - [Stanford's Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task](https://md.research.elamur.ai/free/en/papers/lee-2011-stanford-s-multi-pass-sieve/) - [Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules](https://md.research.elamur.ai/free/en/papers/lee-2013-deterministic-coreference-resolution-based-entity/) - [Graph-Cut-Based Anaphoricity Determination for Coreference Resolution](https://md.research.elamur.ai/free/en/papers/ng-2009-graph-cut-based-anaphoricity-determination/) - [Supervised Noun Phrase Coreference Research: The First Fifteen Years](https://md.research.elamur.ai/free/en/papers/ng-2010-supervised-noun-phrase-coreference-research/) - [An Entity-Mention Model for Coreference Resolution with Inductive Logic Programming](https://md.research.elamur.ai/free/en/papers/yang-2008-entity-mention-model-coreference-resolution/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{yang2007coreference, title = {{Coreference Resolution Using Semantic Relatedness Information from Automatically Discovered Patterns}}, author = {Yang, Xiaofeng and Su, Jian}, booktitle = {Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics}, year = {2007}, url = {https://aclanthology.org/P07-1067/} } ``` - [← previous Coreference or Not: A Twin Model for Coreference Resolution](https://md.research.elamur.ai/free/en/papers/luo-2007-coreference-or-not-twin-model/) - [next → Dependency-Based Construction of Semantic Space Models](https://md.research.elamur.ai/free/en/papers/pado-2007-dependency-based-construction-semantic-space/) - [↑ back to papers of 2007](https://md.research.elamur.ai/free/en/papers/2007/) ## References 16 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. D. Bean and E. Riloff. 2004. Unsupervised learning of contextual role knowledge for coreference resolution. In Proceedings of NAACL, pages 297–304. [find](https://scholar.google.com/scholar?q=D%2E+Bean+and+E%2E+Riloff%2E+2004%2E+Unsupervised+learning+of+contextual+role+knowledge+for+coreference+resolution%2E+In+Proceedings+of+NAACL%2C+pages+297%E2%80%93304%2E) [our card](https://md.research.elamur.ai/free/en/papers/bean-2004-unsupervised-learning-contextual-role-knowledge/) 2. P. Cimiano and S. Staab. 2004. Learning by googling. SIGKDD Explorations Newsletter, 6(2):24–33. [find](https://scholar.google.com/scholar?q=P%2E+Cimiano+and+S%2E+Staab%2E+2004%2E+Learning+by+googling%2E+SIGKDD+Explorations+Newsletter%2C+6%282%29%3A24%E2%80%9333%2E) 3. T. Cover and J. Thomas. 1991. Elements of Information Theory. Hohn Wiley & Sons. [find](https://scholar.google.com/scholar?q=T%2E+Cover+and+J%2E+Thomas%2E+1991%2E+Elements+of+Information+Theory%2E+Hohn+Wiley+%26+Sons%2E) 4. N. Garera and D. Yarowsky. 2006. Resolving and generating definite anaphora by modeling hypernymy using unlabeled corpora. In Proceedings of CoNLL , pages 37–44. [find](https://scholar.google.com/scholar?q=N%2E+Garera+and+D%2E+Yarowsky%2E+2006%2E+Resolving+and+generating+definite+anaphora+by+modeling+hypernymy+using+unlabeled+corpora%2E+In+Proceedings+of+CoNLL+%2C+pages+37%E2%80%9344%2E) 5. S. Harabagiu, R. Bunescu, and S. Maiorano. 2001. Text knowledge mining for coreference resolution. In Proceedings of NAACL, pages 55–62. [find](https://scholar.google.com/scholar?q=S%2E+Harabagiu%2C+R%2E+Bunescu%2C+and+S%2E+Maiorano%2E+2001%2E+Text+knowledge+mining+for+coreference+resolution%2E+In+Proceedings+of+NAACL%2C+pages+55%E2%80%9362%2E) 6. M. Hearst. 1998. Automated discovery of wordnet relations. In Christiane Fellbaum, editor, WordNet: An Electronic Lexical Database and Some of its Applications. MIT Press, Cambridge, MA. [find](https://scholar.google.com/scholar?q=M%2E+Hearst%2E+1998%2E+Automated+discovery+of+wordnet+relations%2E+In+Christiane+Fellbaum%2C+editor%2C+WordNet%3A+An+Electronic+Lexical+Database+and+Some+of+its+Applications%2E+MIT+Press%2C+Cambridge%2C+MA%2E) 7. K. Markert, M. Nissim, and N. Modjeska. 2003. Using the web for nominal anaphora resolution. In Proceedings of the EACL workshop on Computational Treatment of Anaphora, pages 39–46. [find](https://scholar.google.com/scholar?q=K%2E+Markert%2C+M%2E+Nissim%2C+and+N%2E+Modjeska%2E+2003%2E+Using+the+web+for+nominal+anaphora+resolution%2E+In+Proceedings+of+the+EACL+workshop+on+Computational+Treatment+of+Anaphora%2C+pages+39%E2%80%9346%2E) 8. N. Modjeska, K. Markert, and M. Nissim. 2003. Using the web in machine learning for other-anaphora resolution. In Proceedings of EMNLP, pages 176–183. [find](https://scholar.google.com/scholar?q=N%2E+Modjeska%2C+K%2E+Markert%2C+and+M%2E+Nissim%2E+2003%2E+Using+the+web+in+machine+learning+for+other%2Danaphora+resolution%2E+In+Proceedings+of+EMNLP%2C+pages+176%E2%80%93183%2E) [our card](https://md.research.elamur.ai/free/en/papers/modjeska-2003-web-machine-learning-other-anaphora/) 9. V. Ng and C. Cardie. 2002. Improving machine learning approaches to coreference resolution. In Proceedings of ACL, pages 104–111, Philadelphia. [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+Proceedings+of+ACL%2C+pages+104%E2%80%93111%2C+Philadelphia%2E) [our card](https://md.research.elamur.ai/free/en/papers/ng-2002-improving-machine-learning-approaches-coreference/) 10. V. Ng. 2005. Machine learning for coreference resolution: From local classification to global ranking. In Proceedings of ACL, pages 157–164. [find](https://scholar.google.com/scholar?q=V%2E+Ng%2E+2005%2E+Machine+learning+for+coreference+resolution%3A+From+local+classification+to+global+ranking%2E+In+Proceedings+of+ACL%2C+pages+157%E2%80%93164%2E) [our card](https://md.research.elamur.ai/free/en/papers/ng-2005-machine-learning-coreference-resolution-local/) 11. P. Pantel and M. Pennacchiotti. 2006. Espresso: Leveraging generic patterns for automatically harvesting semantic relations. In Proceedings of ACL, pages 113–1200. [find](https://scholar.google.com/scholar?q=P%2E+Pantel+and+M%2E+Pennacchiotti%2E+2006%2E+Espresso%3A+Leveraging+generic+patterns+for+automatically+harvesting+semantic+relations%2E+In+Proceedings+of+ACL%2C+pages+113%E2%80%931200%2E) 12. M. Poesio, R. Mehta, A. Maroudas, and J. Hitzeman. 2004. Learning to resolve bridging references. In Proceedings of ACL, pages 143–150. [find](https://scholar.google.com/scholar?q=M%2E+Poesio%2C+R%2E+Mehta%2C+A%2E+Maroudas%2C+and+J%2E+Hitzeman%2E+2004%2E+Learning+to+resolve+bridging+references%2E+In+Proceedings+of+ACL%2C+pages+143%E2%80%93150%2E) [our card](https://md.research.elamur.ai/free/en/papers/poesio-2004-learning-resolve-bridging-references/) 13. S. Ponzetto and M. Strube. 2006. Exploiting semantic role labeling, wordnet and wikipedia for coreference resolution. In Proceedings of NAACL, pages 192–199. [find](https://scholar.google.com/scholar?q=S%2E+Ponzetto+and+M%2E+Strube%2E+2006%2E+Exploiting+semantic+role+labeling%2C+wordnet+and+wikipedia+for+coreference+resolution%2E+In+Proceedings+of+NAACL%2C+pages+192%E2%80%93199%2E) [our card](https://md.research.elamur.ai/free/en/papers/ponzetto-2006-exploiting-semantic-role-labeling-wordnet/) 14. W. Soon, H. Ng, and D. 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%2E+Soon%2C+H%2E+Ng%2C+and+D%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/en/papers/soon-2001-machine-learning-approach-coreference-resolution/) 15. R. Vieira and M. Poesio. 2000. An empirically based system for processing definite descriptions. Computational Linguistics, 27(4):539–592. [find](https://scholar.google.com/scholar?q=R%2E+Vieira+and+M%2E+Poesio%2E+2000%2E+An+empirically+based+system+for+processing+definite+descriptions%2E+Computational+Linguistics%2C+27%284%29%3A539%E2%80%93592%2E) 16. M. Vilain, J. Burger, J. Aberdeen, D. Connolly, and L. Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the Sixth Message understanding Conference (MUC-6), pages 45–52, San Francisco, CA. Morgan Kaufmann Publishers. [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+Sixth+Message+understanding+Conference+%28MUC%2D6%29%2C+pages+45%E2%80%9352%2C) [our card](https://md.research.elamur.ai/free/en/papers/vilain-1995-model-theoretic-coreference-scoring-scheme/)