Nursing-care text classification using word vector representation and convolutional neural networks

In this paper, we propose a convolutional neural network (CNN) based classification method for nursing-care classification. CNNs have obtained strong performance in computer vision speech recognition areas. Recently, CNNs have been also applied sentence classification. We have studied nursing-care text classification [6]-[18]. In our former works, we proposed several types of feature definitions and examined some classification models. In this paper, each text is represented as a concatenated word vector. Then, every text is classified using CNN-based classification methods. We examined some classification models at the classification layer in CNNs. From our experimental results, the proposed CNN-based method obtained better performance than our former works.

[1]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[2]  Manabu Nii,et al.  A directed graph based feature definition for classifying nursing-care texts , 2014, 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[3]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[4]  Takafumi Yamaguchi,et al.  Analysis of nursing-care freestyle japanese text classification using ga-based term selection , 2010, 2010 World Automation Congress.

[5]  S. Ando,et al.  Feature extraction from nursing-care texts for classification , 2008, 2008 World Automation Congress.

[6]  Geoffrey Zweig,et al.  Linguistic Regularities in Continuous Space Word Representations , 2013, NAACL.

[7]  Yutaka Takahashi,et al.  GA based Feature Selection for Nursing-care Freestyle Text Classification , 2008 .

[8]  Takafumi Yamaguchi,et al.  Classification of Nursing-care Data Using Additional Term Information , 2010 .

[9]  Manabu Nii,et al.  An approach using conceptual fuzzy sets for nursing-care text classification , 2012, World Automation Congress 2012.

[10]  Manabu Nii,et al.  New feature definition for improvement of Nursing-care text classification , 2012, 2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[11]  Manabu Nii,et al.  Feature Definition Using Dependency Relations between Terms for Improving Nursing-care Text Classification , 2012, 2012 Fifth International Conference on Emerging Trends in Engineering and Technology.

[12]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[13]  Manabu Nii,et al.  A matrix-based feature vector definition and a SVM-BDT-based classification system for classifying nursing-care texts , 2015, 2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[14]  Manabu Nii,et al.  Nursing-care text evaluation using word vector representations realized by word2vec , 2016, 2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[15]  Manabu Nii,et al.  Consideration about Utilizing Text Architecture for Making Feature Vectors in Classifying Nursing-Care Texts , 2013, 2013 IEEE International Conference on Systems, Man, and Cybernetics.

[16]  Manabu Nii,et al.  Improving Classification Performance of Nursing-Care Text Classification System by Using GA-Based Term Selection , 2010, J. Adv. Comput. Intell. Intell. Informatics.

[17]  Ye Zhang,et al.  A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification , 2015, IJCNLP.