--- title: "Context-Sensitive Convolution Tree Kernel for — Zhou 2008" description: "This work tackles pronoun resolution, the task of linking a third-person pronoun to its antecedent, using tree kernels over syntactic parses." authors: ["GuoDong Zhou", "Fang Kong", "QiaoMing Zhu"] year: 2008 venue: "Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-I" source: "https://aclanthology.org/I08-1004/" 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-2008-context-sensitive-convolution-tree-kernel/" --- [Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/zhou-2008-context-sensitive-convolution-tree-kernel/) [home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2008](https://md.research.elamur.ai/free/papers/2008/) / Context-Sensitive Convolution Tree Kernel for Pronoun Resolution # Context-Sensitive Convolution Tree Kernel for Pronoun Resolution **Authors:** [GuoDong Zhou](https://md.research.elamur.ai/free/authors/guodong-zhou/), [Fang Kong](https://md.research.elamur.ai/free/authors/fang-kong/), [QiaoMing Zhu](https://md.research.elamur.ai/free/authors/qiaoming-zhu/) · **Year:** 2008 · **Venue:** Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-I · **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/I08-1004/) · [PDF](https://aclanthology.org/I08-1004.pdf) · [OpenAlex](https://openalex.org/W2404513561) **Citations:** 17 citations (openalex-snapshot · 2026-10-14) · [7](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary This work tackles pronoun resolution, the task of linking a third-person pronoun to its antecedent, using tree kernels over syntactic parses. The authors identify two weaknesses in earlier kernel-based work built on Collins and Duffy's convolution tree kernel (Yang et al. 2006). First, enumerated sub-trees ignore everything outside themselves. Second, there is no principled way to choose which part of the parse tree to compare. Their solution has two parts. A dynamic-expansion scheme builds the tree span by starting from the shortest anaphor–candidate path, then adding compatible competing candidates and predicate paths, and finally pruning redundant unary nodes. A context-sensitive convolution tree kernel then also counts sub-trees together with their ancestor node paths. Texts are parsed with the Charniak parser, and classification uses SVMLight. On the ACE 2003 corpus, both components beat earlier tree span schemes and the standard kernel. The dynamic scheme is notably more robust when the antecedent lies in an earlier sentence. The study shows that targeted, context-aware syntactic structure helps more than simply including more of the tree. ## Key points - Evaluation covers third-person pronouns in ACE 2003. Candidate NPs come from the current and two preceding sentences and are filtered by number, person, and gender agreement, leaving about 7 candidates per anaphor. Results are reported as F-measure. - Including ancestor paths of length m = 3 (parent and grandparent context) gives about 2.2 F more than m = 1. Longer paths bring no further gain, likely because of parsing errors. - The dynamic-expansion span outperforms Min-, Simple-, and Full-Expansion by roughly 2.4, 1.2, and 2.1 F, respectively. - Ablation from the full system (83.0 F): removing competitor information costs 1.9, removing predicate information costs 0.8, and removing pruning costs 0.2. - For antecedents two sentences away, the dynamic scheme scores 54.2 F, compared with 43.8 for Simple-Expansion and 35.4 for Full-Expansion. *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 7 papers of our library cite it (of the 140673 whose bibliographies we read); 6 of them have a page here, 1 not yet. - [Chinese Zero Pronoun Resolution: Some Recent Advances](https://md.research.elamur.ai/free/papers/chen-2013-chinese-zero-pronoun-resolution-some/) - [Chinese Zero Pronoun Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers](https://md.research.elamur.ai/free/papers/chen-2014-chinese-zero-pronoun-resolution-unsupervised/) - [Chinese Zero Pronoun Resolution: A Joint Unsupervised Discourse-Aware Model Rivaling State-of-the-Art Resolvers](https://md.research.elamur.ai/free/papers/chen-2015-chinese-zero-pronoun-resolution-joint/) - [Dependency-driven Anaphoricity Determination for Coreference Resolution](https://md.research.elamur.ai/free/papers/kong-2010-dependency-driven-anaphoricity-determination-coreference/) - [A Tree Kernel-Based Unified Framework for Chinese Zero Anaphora Resolution](https://md.research.elamur.ai/free/papers/kong-2010-tree-kernel-based-unified-framework/) - [Global Learning of Noun Phrase Anaphoricity in Coreference Resolution via Label Propagation](https://md.research.elamur.ai/free/papers/zhou-2009-global-learning-noun-phrase-anaphoricity/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{zhou2008context, title = {{Context-Sensitive Convolution Tree Kernel for Pronoun Resolution}}, author = {Zhou, GuoDong and Kong, Fang and Zhu, QiaoMing}, booktitle = {Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-I}, year = {2008}, url = {https://aclanthology.org/I08-1004/} } ``` - [← previous Constructing Corpora for the Development and Evaluation of Paraphrase Systems](https://md.research.elamur.ai/free/papers/cohn-2008-constructing-corpora-development-evaluation-paraphrase/) - [next → Coreference Systems Based on Kernels Methods](https://md.research.elamur.ai/free/papers/versley-2008-coreference-systems-based-kernels-methods/) - [↑ back to papers of 2008](https://md.research.elamur.ai/free/papers/2008/) ## References 20 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Aone C and Bennett W.W. (1995). Evaluating automated and manual acquisition of anaphora resolution strategies. ACL’1995:122-129. [find](https://scholar.google.com/scholar?q=Aone+C+and+Bennett+W%2EW%2E+%281995%29%2E+Evaluating+automated+and+manual+acquisition+of+anaphora+resolution+strategies%2E+ACL%E2%80%991995%3A122%2D129%2E) [our card](https://md.research.elamur.ai/free/papers/aone-1995-evaluating-automated-manual-acquisition-anaphora/) 2. Bergsma S. and Lin D.K.(2006). Bootstrapping path-based pronoun resolution. COLING-ACL’2006: 33-40. [find](https://scholar.google.com/scholar?q=Bergsma+S%2E+and+Lin+D%2EK%2E%282006%29%2E+Bootstrapping+path%2Dbased+pronoun+resolution%2E+COLING%2DACL%E2%80%992006%3A+33%2D40%2E) [our card](https://md.research.elamur.ai/free/papers/bergsma-2006-bootstrapping-path-based-pronoun-resolution/) 3. Charniak E. (2001). Immediate-head Parsing for Language Models. ACL’2001: 129-137. [find](https://scholar.google.com/scholar?q=Charniak+E%2E+%282001%29%2E+Immediate%2Dhead+Parsing+for+Language+Models%2E+ACL%E2%80%992001%3A+129%2D137%2E) [our card](https://md.research.elamur.ai/free/papers/charniak-2001-immediate-head-parsing-language-models/) 4. Toulouse, France Collins M. (1999) Head-driven statistical models for natural language parsing. Ph.D. Thesis. University of Pennsylvania. [find](https://scholar.google.com/scholar?q=Toulouse%2C+France+Collins+M%2E+%281999%29+Head%2Ddriven+statistical+models+for+natural+language+parsing%2E+Ph%2ED%2E+Thesis%2E+University+of+Pennsylvania%2E) 5. Collins M. and Duffy N. (2001). Convolution Kernels for Natural Language. NIPS’2001: 625-632. [find](https://scholar.google.com/scholar?q=Collins+M%2E+and+Duffy+N%2E+%282001%29%2E+Convolution+Kernels+for+Natural+Language%2E+NIPS%E2%80%992001%3A+625%2D632%2E) 6. Cambridge, MA Culotta A. and Sorensen J. (2004). Dependency tree kernels for relation extraction. ACL’2004. 423-429. 21-26 July 2004. Barcelona, Spain. [find](https://scholar.google.com/scholar?q=Cambridge%2C+MA+Culotta+A%2E+and+Sorensen+J%2E+%282004%29%2E+Dependency+tree+kernels+for+relation+extraction%2E+ACL%E2%80%992004%2E+423%2D429%2E+21%2D26+July+2004%2E+Barcelona%2C+Spain%2E) 7. Haussler D. (1999). Convolution Kernels on Discrete Structures. Technical Report UCS-CRL-99-10, University of California, Santa Cruz. [find](https://scholar.google.com/scholar?q=Haussler+D%2E+%281999%29%2E+Convolution+Kernels+on+Discrete+Structures%2E+Technical+Report+UCS%2DCRL%2D99%2D10%2C+University+of+California%2C+Santa+Cruz%2E) 8. Hobbs J. (1978). Resolving pronoun references. Lingua. 44:339-352. [find](https://scholar.google.com/scholar?q=Hobbs+J%2E+%281978%29%2E+Resolving+pronoun+references%2E+Lingua%2E+44%3A339%2D352%2E) [our card](https://md.research.elamur.ai/free/papers/hobbs-1978-resolving-pronoun-references/) 9. Joachims T. (1998). Text Categorization with Support Vector Machine: learning with many relevant features. ECML-1998: 137-142. [find](https://scholar.google.com/scholar?q=Joachims+T%2E+%281998%29%2E+Text+Categorization+with+Support+Vector+Machine%3A+learning+with+many+relevant+features%2E+ECML%2D1998%3A+137%2D142%2E) 10. Chemnitz, Germany Lappin S. and Leass H. (1994). An algorithm for pronominal anaphora resolution. Computational Linguistics. 20(4):526-561. [find](https://scholar.google.com/scholar?q=Chemnitz%2C+Germany+Lappin+S%2E+and+Leass+H%2E+%281994%29%2E+An+algorithm+for+pronominal+anaphora+resolution%2E+Computational+Linguistics%2E+20%284%29%3A526%2D561%2E) [our card](https://md.research.elamur.ai/free/papers/lappin-1994-algorithm-pronominal-anaphora-resolution/) 11. Mitkov R. (1998). Robust pronoun resolution with limited knowledge. COLING-ACL’1998:869-875. Montreal, Canada. [find](https://scholar.google.com/scholar?q=Mitkov+R%2E+%281998%29%2E+Robust+pronoun+resolution+with+limited+knowledge%2E+COLING%2DACL%E2%80%991998%3A869%2D875%2E+Montreal%2C+Canada%2E) [our card](https://md.research.elamur.ai/free/papers/mitkov-1998-robust-pronoun-resolution-limited-knowledge/) 12. Moschitti A. (2004). A study on convolution kernels for shallow semantic parsing. ACL’2004:335-342. [find](https://scholar.google.com/scholar?q=Moschitti+A%2E+%282004%29%2E+A+study+on+convolution+kernels+for+shallow+semantic+parsing%2E+ACL%E2%80%992004%3A335%2D342%2E) 13. Pradhan S., Hacioglu K., Krugler V., Ward W., Martin J.H. and Jurafsky D. (2005). Support Vector Learning for Semantic Argument Classification. Machine Learning. 60(1):11-39. [find](https://scholar.google.com/scholar?q=Pradhan+S%2E%2C+Hacioglu+K%2E%2C+Krugler+V%2E%2C+Ward+W%2E%2C+Martin+J%2EH%2E+and+Jurafsky+D%2E+%282005%29%2E+Support+Vector+Learning+for+Semantic+Argument+Classification%2E+Machine+Learning%2E+60%281%29%3A11%2D39%2E) 14. Soon W. Ng H.T.and Lim D. (2001). A machine learning approach to creference resolution of noun phrases. Computational Linguistics. 27(4): 521-544. [find](https://scholar.google.com/scholar?q=Soon+W%2E+Ng+H%2ET%2Eand+Lim+D%2E+%282001%29%2E+A+machine+learning+approach+to+creference+resolution+of+noun+phrases%2E+Computational+Linguistics%2E+27%284%29%3A+521%2D544%2E) 15. Yang X.F., Zhou G.D., Su J. and Tan C.L., Coreference Resolution Using Competition Learning Approach, ACL’2003):176-183. Sapporo, Japan, 7-12 July 2003. [find](https://scholar.google.com/scholar?q=Yang+X%2EF%2E%2C+Zhou+G%2ED%2E%2C+Su+J%2E+and+Tan+C%2EL%2E%2C+Coreference+Resolution+Using+Competition+Learning+Approach%2C+ACL%E2%80%992003%29%3A176%2D183%2E+Sapporo%2C+Japan%2C+7%2D12+July+2003%2E) [our card](https://md.research.elamur.ai/free/papers/yang-2003-coreference-resolution-competition-learning-approach/) 16. Yang X.F., Su J. and Tan C.L. (2006). Kernel-based pronoun resolution with structured syntactic knowledge. COLING-ACL’2006: 41-48. [find](https://scholar.google.com/scholar?q=Yang+X%2EF%2E%2C+Su+J%2E+and+Tan+C%2EL%2E+%282006%29%2E+Kernel%2Dbased+pronoun+resolution+with+structured+syntactic+knowledge%2E+COLING%2DACL%E2%80%992006%3A+41%2D48%2E) [our card](https://md.research.elamur.ai/free/papers/yang-2006-kernel-based-pronoun-resolution-structured/) 17. Zelenko D., Aone C. and Richardella. (2003). Kernel methods for relation extraction. Journal of Machine Learning Research. 3(Feb):1083-1106. [find](https://scholar.google.com/scholar?q=Zelenko+D%2E%2C+Aone+C%2E+and+Richardella%2E+%282003%29%2E+Kernel+methods+for+relation+extraction%2E+Journal+of+Machine+Learning+Research%2E+3%28Feb%29%3A1083%2D1106%2E) 18. Zhang M., Zhang J., Su J. and Zhou G.D. (2006). A Composite Kernel to Extract Relations between Entities with both Flat and Structured Features. COLING-ACL-2006: 825-832. [find](https://scholar.google.com/scholar?q=Zhang+M%2E%2C+Zhang+J%2E%2C+Su+J%2E+and+Zhou+G%2ED%2E+%282006%29%2E+A+Composite+Kernel+to+Extract+Relations+between+Entities+with+both+Flat+and+Structured+Features%2E+COLING%2DACL%2D2006%3A+825%2D832%2E) 19. Sydney, Australia Zhou G.D., Su J. Zhang J. and Zhang M. (2005). Exploring various knowledge in relation extraction. ACL’2005. 427-434. 25-30 June, Ann Arbor, Mich-gan, USA. [find](https://scholar.google.com/scholar?q=Sydney%2C+Australia+Zhou+G%2ED%2E%2C+Su+J%2E+Zhang+J%2E+and+Zhang+M%2E+%282005%29%2E+Exploring+various+knowledge+in+relation+extraction%2E+ACL%E2%80%992005%2E+427%2D434%2E+25%2D30+June%2C+Ann+Arbor%2C+Mich%2Dgan%2C+USA%2E) 20. Zhou G.D., Zhang M., Ji D.H. and Zhu Q.M. (2007). Tree Kernel-based Relation Extraction with Context-Sensitive Structured Parse Tree Information. EMNLP-CoNLL’2007 [find](https://scholar.google.com/scholar?q=Zhou+G%2ED%2E%2C+Zhang+M%2E%2C+Ji+D%2EH%2E+and+Zhu+Q%2EM%2E+%282007%29%2E+Tree+Kernel%2Dbased+Relation+Extraction+with+Context%2DSensitive+Structured+Parse+Tree+Information%2E+EMNLP%2DCoNLL%E2%80%992007)