[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
article

Exploring syntactic structured features over parse trees for relation extraction using kernel methods

Published: 01 March 2008 Publication History

Abstract

Extracting semantic relationships between entities from text documents is challenging in information extraction and important for deep information processing and management. This paper proposes to use the convolution kernel over parse trees together with support vector machines to model syntactic structured information for relation extraction. Compared with linear kernels, tree kernels can effectively explore implicitly huge syntactic structured features embedded in a parse tree. Our study reveals that the syntactic structured features embedded in a parse tree are very effective in relation extraction and can be well captured by the convolution tree kernel. Evaluation on the ACE benchmark corpora shows that using the convolution tree kernel only can achieve comparable performance with previous best-reported feature-based methods. It also shows that our method significantly outperforms previous two dependency tree kernels for relation extraction. Moreover, this paper proposes a composite kernel for relation extraction by combining the convolution tree kernel with a simple linear kernel. Our study reveals that the composite kernel can effectively capture both flat and structured features without extensive feature engineering, and easily scale to include more features. Evaluation on the ACE benchmark corpora shows that the composite kernel outperforms previous best-reported methods in relation extraction.

References

[1]
ACE (2002-2006). The Automatic Content Extraction (ACE) projects. Available from http://www.ldc.upenn.edu/Projects/ACE/.
[2]
Bunescu, R. C., & Mooney, R. J. (2005). A shortest path dependency kernel for relation extraction. EMNLP-2005, Vancouver, BC (pp. 724-731)
[3]
Charniak, E. (2001). Immediate-head parsing for language models. ACL-2001, Toulouse, France (pp 129-137).
[4]
Collins, M., & Duffy, N. (2001). Convolution kernels for natural language. NIPS-2001, Cambridge, MA (pp. 625-632).
[5]
Culotta, A., & Sorensen, J. (2004). Dependency tree kernel for relation extraction. ACL-2004, Barcelona, Spain (pp. 423-429).
[6]
Haussler, D. (1999). Convolution kernels on discrete structures. Technical Report UCS-CRL-99-10, University of California, Santa Cruz.
[7]
Joachims, T. (1998). Text categorization with support vector machine: Learning with many relevant features. ECML-1998, Chemnitz, Germany (pp. 137-142).
[8]
Kambhatla, N. (2004). Combining lexical, syntactic and semantic features with Maximum Entropy models for extracting relations. ACL-2004 (poster), Barcelona, Spain (pp. 178-181).
[9]
Text classification using string kernel. Journal of Machine Learning Research. v2002 i2. 419-444.
[10]
Miller, S., Fox, H., Ramshaw, L., & Weischedel, R. (2000). A novel use of statistical parsing to extract information from text. ANLP'2000, Seattle, USA (pp. 226-233).
[11]
Moschitti, A. (2004). A study on convolution kernels for shallow semantic parsing. ACL-2004, Barcelona, Spain (pp. 335-342).
[12]
MUC (1987-1998). The NIST MUC website: http://www.itl.nist.gov/iaui/894.02/related_projects/muc/.
[13]
Learning with kernels: SVM, regularization, optimization and beyond. MIT Press, Cambridge, MA.
[14]
Suzuki, J., Hirao, T., Sasaki, Y., & Maeda, E., (2003). Hierarchical directed acyclic graph kernel: Methods for structured natural language data. ACL-2003, Sapporo, Japan (pp. 33-40).
[15]
Statistical learning theory. Whiley, Chichester, GB.
[16]
Vishwanathan, S. V. N., & Smola, A. J. (2002). Fast kernels for string and tree matching. NIPS-2002, Vancouver, Canada (pp. 569-576).
[17]
Zhao, S., & Grishman, R. (2005). Extracting relations with integrated information using kernel methods. ACL-2005, Ann Arbor, USA (pp. 419-426).
[18]
Kernel methods for relation extraction. Journal of Machine Learning Research. v2003 i2. 1083-1106.
[19]
Zhou, G., Su, J., Zhang, J., & Zhang, M. (2005). Exploring various knowledge in relation extraction. ACL-2005, Ann Arbor, USA (pp. 427-434).
[20]
Zhang, M., Zhang, J., Su, J., & Zhou, G. (2006). A composite kernel to extract relations between entities with both flat and structured features. COLING-ACL-2006, Sydney, Australia (pp. 825-832).

Cited By

View all

Recommendations

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Information Processing and Management: an International Journal
Information Processing and Management: an International Journal  Volume 44, Issue 2
March, 2008
562 pages

Publisher

Pergamon Press, Inc.

United States

Publication History

Published: 01 March 2008

Author Tags

  1. Composite kernel
  2. Convolution tree kernel
  3. Information extraction
  4. Relation extraction
  5. Syntactic structured features

Qualifiers

  • Article

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)0
  • Downloads (Last 6 weeks)0
Reflects downloads up to 12 Dec 2024

Other Metrics

Citations

Cited By

View all
  • (2023)MusRELInternational Journal on Semantic Web & Information Systems10.4018/IJSWIS.32996519:1(1-19)Online publication date: 8-Sep-2023
  • (2022)Weighted graph convolution over dependency trees for nontaxonomic relation extraction on public opinion informationApplied Intelligence10.1007/s10489-021-02596-952:3(3403-3417)Online publication date: 1-Feb-2022
  • (2021)Named Entity Recognition and Relation ExtractionACM Computing Surveys10.1145/344596554:1(1-39)Online publication date: 11-Feb-2021
  • (2019)Combating Fake NewsACM Transactions on Intelligent Systems and Technology10.1145/330526010:3(1-42)Online publication date: 12-Apr-2019
  • (2017)Ontology of human relation extraction based on dependency syntax rulesProceedings of the International Conference on Web Intelligence10.1145/3106426.3109050(1151-1157)Online publication date: 23-Aug-2017
  • (2016)An ensemble method for extracting adverse drug events from social mediaArtificial Intelligence in Medicine10.1016/j.artmed.2016.05.00470:C(62-76)Online publication date: 1-Jun-2016
  • (2014)Learning subgraph patterns from text for extracting disease-symptom relationshipsProceedings of the 1st International Conference on Interactions between Data Mining and Natural Language Processing - Volume 120210.5555/3053762.3053769(81-96)Online publication date: 15-Sep-2014
  • (2014)Region-based association measures for ranking mined news relationsIntelligent Data Analysis10.5555/2639292.263929918:2(217-241)Online publication date: 1-Mar-2014
  • (2014)An intensive case study on kernel-based relation extractionMultimedia Tools and Applications10.1007/s11042-013-1380-571:2(741-767)Online publication date: 1-Jul-2014
  • (2013)Machine learning of syntactic parse trees for search and classification of textEngineering Applications of Artificial Intelligence10.1016/j.engappai.2012.09.01726:3(1072-1091)Online publication date: 1-Mar-2013
  • Show More Cited By

View Options

View options

Login options

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media