Feature-Based Relation Classification Using Quantified Relatedness Information

ETRI Journal

关键词: feature-based;    probabilistic relatedness;    semantic relatedness;    feature selection;    Relation classification;   

Others  :  1185952
DOI  :  10.4218/etrij.10.0209.0353

【 摘 要 】

Feature selection is very important for feature-based relation classification tasks. While most of the existing works on feature selection rely on linguistic information acquired using parsers, this letter proposes new features, including probabilistic and semantic relatedness features, to manifest the relatedness between patterns and certain relation types in an explicit way. The impact of each feature set is evaluated using both a chi-square estimator and a performance evaluation. The experiments show that the impact of relatedness features is superior to existing well-known linguistic features, and the contribution of relatedness features cannot be substituted using other normally used linguistic feature sets.

   

【 参考文献 】

• [1]N. Kambhatla, "Combining Lexical, Syntactic, and Semantic Features with Maximum Entropy Models for Extracting Relations," Proc. 42nd ACL, 2004, article no. 22.
• [2]G. Zhou and M. Zhang, "Extracting Relation Information from Text Documents by Exploring Various Types of Knowledge," Inf. Process Manage., vol. 43, no. 4, 2007, pp. 969-982.
• [3]Z. Zhang, "Mining Relational Data from Text: From Strictly Supervised to Weakly Supervised Learning," Inf. Syst., vol. 33, no. 3, 2008, pp. 300-314.
• [4]R. Girju, A. Badulescu, and D. Moldovan, "Automatic Discovery of Part-Whole Relations," Computational Linguistics, vol. 32, no. 1, 2006, pp. 83-135.
• [5]H. Liu and P. Singh, "ConceptNet: A Practical Commonsense Reasoning Tool-Kit," BT Technol. J., vol. 22, no. 4, 2004, pp. 211-226.
• [6]J.X. Huang, J.A. Shin, and K.S. Choi, "Enriching Core Ontology with Domain Thesaurus through Concept and Relation Classification," Proc. OntoLex, ISWC, 2007.
• [7]J. Cohen, "A Coefficient of Agreement for Nominal Scales," Educational and Psychological Measurement, vol. 20, no. 1, 1960, p. 37.
• [8]H.J. Oh, S.H. Myaeng, and M.G. Jang, "Enhancing Performance with a Learnable Strategy for Multiple Question Answering Modules," ETRI J., vol. 31, no. 4, Aug. 2009, pp. 419-428.
• [9]Y.S. Hwang and Y.K. Kim, "Automatic Acquisition of Paraphrases Using Bilingual Dependency Relations," ETRI J., vol. 30, no. 1, Feb. 2008, pp. 155-157.