Applying a multitask feature sparsity method for the classification of semantic relations between nominals

Author

Chao, Guoqing ; Sun, Shiliang

Author_Institution

Dept. of Comput. Sci. & Technol., East China Normal Univ., Shanghai, China

Volume

1

fYear

2012

fDate

15-17 July 2012

Firstpage

72

Lastpage

76

Abstract

This paper extracts seven effective feature sets and reduces them to same dimension by principle component analysis (peA), such that it can utilize a multitask feature sparsity approach to the automatic identification of semantic relations between nominals in English sentences under maximum entropy discrimination (MED) framework. This method can make full use of related information between different semantic classifications to perform multitask discriminative learning and don´t employ additional knowledge sources. At SemEval 2007, our system achieved a F-score of 69.15 % which is higher than that by independent SVM.

Keywords

feature extraction; learning (artificial intelligence); maximum entropy methods; natural language processing; pattern classification; principal component analysis; text analysis; English sentences; F-score; MED framework; PCA; SemEval 2007; automatic semantic relations identification; feature set extraction; maximum entropy discrimination; multitask discriminative learning; multitask feature sparsity method; nominals; principal component analysis; semantic relations classification; Abstracts; Containers; Instruments; Sun; Support vector machines; Maximum entropy discrimination; Multitask learning; Semantic relation; Support vector machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics (ICMLC), 2012 International Conference on

Conference_Location

Xian

ISSN

2160-133X

Print_ISBN

978-1-4673-1484-8

Type

conf

DOI

10.1109/ICMLC.2012.6358889

Filename

6358889