Liangyu Lv

With the number of smart contracts growing rapidly, retrieving the relevant smart contracts quickly and accurately has become an important issue. A key step for recognizing the related smart contracts is able to classify them accurately. Different from traditional text, the smart contract is composed of several parts: source code, code comments and other useful information like account information. How to make good use of those different kinds of features for effective classification is a problem need to be solved. Inspired by this, we proposed a smart contract classification approach based on Bi-LSTM model and Gaussian LDA, which can use a variety of information as inputs of the model, including source code, comments, tags, account and other content information. Bi-LSTM is utilized to capture grammar rules and context information in source code, while Gaussian LDA model is employed to generate comments feature where the semantics of the comments are enriched by embeddings. We also use attention mechanism to focus on the more relevant features in smart contracts for tags and fuse account information to provide additional information for classification. The experimental results show that the classification performance of the proposed model is superior to other baseline models.

The goal of aspect-level sentiment analysis is to identify the sentiment polarity of a specific opinion target expressed; it is a fine-grained sentiment analysis task. Most of the existing works study how to better use the target information to model the sentence without using the interactive information between the sentence and target. In this article, we argue that the prediction of aspect-level sentiment polarity depends on both context and target. First, we propose a new model based on LSTM and the attention mechanism to predict the sentiment of each target in the review, the matrix-interactive attention network (M-IAN) that models target and context, respectively. M-IAN use an attention matrix to learn the interactive attention of context and target and generates the final representations of target and context. Then we introduce two gate networks based on M-IAN to build a deep interactive memory network to capture multiple interactions of target and context. The deep interactive memory network can excellently formulate specific memory for different targets, which is helpful in sentiment analysis. The experimental results of Restaurant and Laptop datasets of SemEval 2014 validate the effectiveness of our model.

Information retrieval-based Web service discovery approach suffers from the semantic sparsity problem caused by lacking of statistical information when the Web services are described in short texts. To handle this problem, external information is often utilized to improve the discovery performance. Inspired by this, we propose a novel Web service discovery approach based on a neural topic model and leveraging Web service labels. More specifically, words in Web services are mapped into continuous embeddings, and labels are integrated by a neural topic model simultaneously for embodying external semantics of the Web service description. Based on the topic model, the services are interpreted into hierarchical models for building a service querying and ranking model. Extensive experiments on several datasets demonstrated that the proposed approach achieves improved performance in terms of F-measure. The results also suggest that leveraging external information is useful for semantic sparse Web service discovery.