Web Services Classification Based on Wide & Bi-LSTM Model

Abstract

With the rapid growth of Web services on the Internet, it becomes a great challenge for Web services discovery. Classifying Web services with similar functions is an effective method for service discovery and management. However, the functional description documents of Web services usually are short in their length, with sparse features and less information, which makes most topic models unable to model the short text well, consequently affecting the Web service classification. To solve this problem, a Web service classification method based on Wide & Bi-LSTM model is proposed in this paper. In this method, first, all the discrete features in the description documents of Web services are combined to perform the breadth prediction of Web service category by exploiting the wide learning model. Second, the word order and context information of the words in the description documents of Web services are mined by using the Bi-LSTM model to perform the depth prediction of the Web service category. Third, it uses the linear regression algorithm to integrate the breadth and depth prediction results of Web service categories as the final result of the service classification. Finally, compared with six Web service classification methods based on TF-IDF, LDA, WE-LDA, LSTM, Wide&Deep, and Bi-LSTM, respectively, the experimental results show that our approach achieves a better performance in the accuracy of Web service classification.INDEX TERMS Wide learning model, Bi-LSTM model, linear regression, web service classification.

The Influencing Legal and Factors of Migrant Children’s Educational Integration Based on Convolutional Neural Network

“…For the MPOA data set, the text category is 2, the average sentence length is 3, the training set contains 9,500 words, and the testing set contains 1,105 words. The classification effects of LSTM ( Chen et al, 2020 ), Bi-LSTM ( Ye et al, 2019 ), Text CNN ( Xie et al, 2020 ), Text RCNN ( Huang et al, 2021 ), attention-based LSTM (ALSTM) ( Liu et al, 2018 ), and attention-based Bi-LSTM (ABi-LSTM) ( Song et al, 2018 ) are compared. The number of hidden layer neurons in the LSTM, Bi-LSTM, GRU, and RCNN model is set to 128, the text batch size is set to 100, the convolution kernel size in the CNN model is set to 3*3, and the number of convolution kernels is set to 128.…”

“…For the MPOA data set, the text category is 2, the average sentence length is 3, the training set contains 9,500 words, and the testing set contains 1,105 words. The classification effects of LSTM (Chen et al, 2020), Bi-LSTM (Ye et al, 2019), Text CNN (Xie et al, 2020), Text RCNN (Huang et al, 2021), attention-based LSTM (ALSTM) (Liu et al, 2018), and attention-based Bi-LSTM (ABi-LSTM) (Song et al, 2018) The difference in classification accuracy of different models on different data sets is quantitatively analyzed, and the results are shown in Table 1. Compared with the LSTM, Bi-LSTM, TextCNN, TextRCNN, ALSTM, and ABi-LSTM models, the classification accuracy of the ALGCNN model constructed on the MR data set is improved by 26.5, 32.3, 6.6, 3.9, 9.0, and 3.5%, respectively; the classification accuracy on the SST data set of the ALGCNN model constructed has increased by 25.0, 29.8, 2.0, 0.0, 14.2, and 8.0%, respectively; and the classification accuracy rate on the MPQA data set has increased by 20.6, 17.3, 6.0, 2.1, 9.2, and 2.9%, respectively.…”

Web Information Extraction methods using Web Content Mining (WCM) for Webapplications

“…Ye et al [19] proposed the methods to find the web services discovery using the deep mining concepts. In this method, web services classification can be done by TF-IDF, LDA, and WE-LDA algorithms from the data warehouse.…”

“…All the text, audio, video, and graphics files are working under one umbrella named multimedia contents and that will be extracted using their textures such as histogram matching concepts, shot boundary detection, and SKICAT tools effectively. The size of the data used here is huge so modern tools are used for extracting accurate data [19]. The following figure 4 describes the techniques used in web content mining concepts.…”

Chinese Microblog Sentiment Detection Based on CNN-BiGRU and Multihead Attention Mechanism

“…Experimental results presented that a small number of poisoned samples can obtain a higher attack success rate. Ye et al [12] proposed a Web service classification method based on WiDE and BI-LSTM model. e wide area learning model was applied to realize the width prediction of the Web service category, which captured the interaction between feature vectors of Web service description documents.…”