Skip to main navigation Skip to search Skip to main content

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

  • Qunbo Wang
  • , Wenjun Wu
  • , Yongchi Zhao
  • , Yuzhang Zhuang
  • , Yanni Wang
  • Beihang University
  • Capital University of Physical Education and Sports

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE International Conference on Web Services, ICWS 2021
EditorsCarl K. Chang, Ernesto Damiani, Jing Fan, Parisa Ghodous, Michael Maximilien, Zhongjie Wang, Robert Ward, Jia Zhang
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages358-363
Number of pages6
ISBN (Electronic)9781665416818
DOIs
StatePublished - 2021
Event2021 IEEE International Conference on Web Services, ICWS 2021 - Virtual, Online, United States
Duration: 5 Sep 202111 Sep 2021

Publication series

NameProceedings - 2021 IEEE International Conference on Web Services, ICWS 2021

Conference

Conference2021 IEEE International Conference on Web Services, ICWS 2021
Country/TerritoryUnited States
CityVirtual, Online
Period5/09/2111/09/21

Keywords

  • BERT Fine-tuning
  • Deep Learning
  • Generative Adversarial Training
  • Label-wise Attention
  • Tag Prediction
  • Web Services

Fingerprint

Dive into the research topics of 'Combining Label-wise Attention and Adversarial Training for Tag Prediction of Web Services'. Together they form a unique fingerprint.

Cite this