Combining Label-wise Attention and Adversarial Training for Tag Prediction of Web Services

Abstract

Tagging is well regarded as one of the best ways of managing web services, in which keywords are assigned by users to describe the published services. As users are required to select multiple tags from a large set of candidate tags based on their own understanding, such user-attached tags are not always reliable and may affect the efficiency of service discovery. To alleviate the issue, tag prediction can suggest users appropriate tags for web services based on the textual descriptions of their functionality. Therefore, it is necessary to design tag prediction methods to support service search and recommendation. In this work, we propose a tag prediction model that adopts BERT-based label-wise attention mechanism, and use adversarial training to further improve the model performance. Experimental results on the service datasets collected from ProgrammableWeb show that the proposed method can achieve better prediction performance than other state-of-art methods.