Text clustering algorithm based on deep representation learning. Issue 16 (22nd October 2018)

• Record Type: Journal Article
• Authors: Wang, Binyu; Liu, Wenfen; Lin, Zijie; Hu, Xuexian; Wei, Jianghong; Liu, Chun
• Is Part Of: Journal of engineering. Volume 2018:Issue 16(2018)
• Page Start: 1407
• Page End: 1414
• Publication Date: 2018-10-22
• Subjects: text analysis -- feature extraction -- pattern clustering -- learning (artificial intelligence); text information -- text representation model -- deep representation learning -- transfer learning domain adaptation -- parameters update -- source domain data -- deep learning classification model -- domain discriminator -- domain‐divide -- domain adaptation problem -- text feature vectors -- MCSKM++ algorithm -- clustering iteration process -- expectation maximisation algorithm -- target domain data -- text clustering result -- model pre‐training problem -- unsupervised clustering -- transfer problem -- domain labels -- clustering accuracy -- text clustering algorithm; Engineering -- Periodicals; Engineering; Electronic journals; Periodicals; 620.005
• DOI: 10.1049/joe.2018.8282
• Languages: English
• ISSNs: 2051-3305

Abstract

Abstract : Text clustering is an important method for effectively organising, summarising, and navigating text information. However, in the absence of labels, the text data to be clustered cannot be used to train the text representation model based on deep learning. To address the problem, an algorithm of text clustering based on deep representation learning is proposed using the transfer learning domain adaptation and the parameters update during cluster iteration. First, source domain data is used to perform the pre‐training of the deep learning classification model. This procedure acts as an initialisation of the model parameters. Then, the domain discriminator is added to the model, to domain‐divide the input sample. If the discriminator cannot distinguish which domain the data belongs to, the common feature space of two domains is obtained, so the domain adaptation problem is solved. Finally, the text feature vectors obtained by the model are clustered with MCSKM++ algorithm. The algorithm not only resolves the model pre‐training problem in unsupervised clustering, but also has a good clustering effect on the transfer problem caused by different numbers of domain labels. Experiments suggest that the clustering accuracy of the algorithm is superior to other similar algorithms.