Support Vector Machine with Ensemble Tree Kernel for Relation Extraction

Relation extraction is one of the important research topics in the field of information extraction research. To solve the problem of semantic variation in traditional semisupervised relation extraction algorithm, this paper proposes a novel semisupervised relation extraction algorithm based on ensemble learning (LXRE). The new algorithm mainly uses two kinds of support vector machine classifiers based on tree kernel for integration and integrates the strategy of constrained extension seed set. The new algorithm can weaken the inaccuracy of relation extraction, which is caused by the phenomenon of semantic variation. The numerical experimental research based on two benchmark data sets (PropBank and AIMed) shows that the LXRE algorithm proposed in the paper is superior to other two common relation extraction methods in four evaluation indexes (Precision, Recall, F-measure, and Accuracy). It indicates that the new algorithm has good relation extraction ability compared with others.

[1]  Yakushiji.  Biomedical Information Extraction with Predicate-Argument Structure Patterns , 2005 .

[2]  Dong-Hong Ji,et al.  Semi-supervised Relation Extraction with Label Propagation , 2006, HLT-NAACL.

[3]  Alexander J. Smola,et al.  Fast Kernels for String and Tree Matching , 2002, NIPS.

[4]  Alessandro Moschitti,et al.  Embedding Semantic Similarity in Tree Kernels for Domain Adaptation of Relation Extraction , 2013, ACL.

[5]  Oren Etzioni,et al.  Self-supervised Relation Extraction from the Web , 2006, ISMIS.

[6]  Hans Uszkoreit,et al.  Analysis and Improvement of Minimally Supervised Machine Learning for Relation Extraction , 2009, NLDB.

[7]  Feng Yansong,et al.  Extracting Relations from the Web via Weakly Supervised Learning , 2013 .

[8]  Rui Guo,et al.  A distributed meta-learning system for Chinese entity relation extraction , 2015, Neurocomputing.

[9]  Wang Yan-hu.  Protein-Protein Interaction Extraction Based on the Combination of Supervised and Semi-Supervised Learning Method , 2013 .

[10]  Roberto Basili,et al.  Tree Kernels for Semantic Role Labeling , 2008, CL.

[11]  Fang Kong,et al.  Semi-Supervised Learning for Semantic Relation Classification using Stratified Sampling Strategy , 2009, EMNLP.

[12]  Masaki Murata,et al.  Extracting Protein-Protein Interaction Information from Biomedical Text with SVM , 2006, IEICE Trans. Inf. Syst..

[13]  Li Li,et al.  A Survey on Relation Extraction , 2017, CCKS.

[14]  Zhu Zhang,et al.  Weakly-supervised relation classification for information extraction , 2004, CIKM '04.

[15]  Hans Uszkoreit,et al.  Boosting Relation Extraction with Limited Closed-World Knowledge , 2010, COLING.

[16]  Mark Stevenson,et al.  Improving Semi-supervised Acquisition of Relation Extraction Patterns , 2006 .

[17]  Hans Uszkoreit,et al.  Adaptation of Relation Extraction Rules to New Domains , 2008, LREC.

[18]  Alessandro Moschitti,et al.  A Study on Convolution Kernels for Shallow Statistic Parsing , 2004, ACL.

[19]  Dragomir R. Radev,et al.  Semi-Supervised Classification for Extracting Protein Interaction Sentences using Dependency Parsing , 2007, EMNLP.

[20]  Chen Jin-Xiu,et al.  Graph-Based Semi-Supervised Relation Extraction , 2008 .

[21]  J. Curran,et al.  Minimising semantic drift with Mutual Exclusion Bootstrapping , 2007 .

[22]  Dong-Hong Ji,et al.  Graph-Based Semi-Supervised Relation Extraction: Graph-Based Semi-Supervised Relation Extraction , 2009 .

[23]  Chunyun Zhang,et al.  Construction of semantic bootstrapping models for relation extraction , 2015, Knowl. Based Syst..

[24]  Alessandro Moschitti,et al.  Distant Supervision for Relation Extraction Using Tree Kernels , 2015, IIR.

[25]  Chen Jin.  Graph-Based Semi-Supervised Relation Extraction , 2008 .

[26]  Zhang Xiao.  Research of protein-protein interaction extraction based on semi-supervised learning , 2009 .

[27]  Zhao Junzhe.  Named Entity Relation Extraction Method Based on Seed Self-expansion , 2006 .

[28]  권홍우,et al.  Bootstrapping , 2002, ACL.

[29]  Takashi Chikayama,et al.  Wide-coverage relation extraction from MEDLINE using deep syntax , 2015, BMC Bioinformatics.

[30]  Deyu Zhou,et al.  A semi-supervised learning framework for biomedical event extraction based on hidden topics , 2015, Artif. Intell. Medicine.

[31]  Michael Collins,et al.  New Ranking Algorithms for Parsing and Tagging: Kernels over Discrete Structures, and the Voted Perceptron , 2002, ACL.

[32]  Rohit J. Kate,et al.  Comparative experiments on learning information extractors for proteins and their interactions , 2005, Artif. Intell. Medicine.

[33]  Hans Uszkoreit,et al.  A Seed-driven Bottom-up Machine Learning Framework for Extracting Relations of Various Complexity , 2007, ACL.

[34]  Alessandro Moschitti,et al.  Making Tree Kernels Practical for Natural Language Learning , 2006, EACL.