bi-directional Bayesian probabilistic model based hybrid grained semantic matchmaking for Web service discovery

• DOI: 10.1007/s11280-022-01004-7
• Publication Date: 2022-02-17T01:03:17Z
• Authors: Shuangyin Li; Haoyu Luo; Gansen Zhao; Mingdong Tang; Xiao Liu
• Keywords: Paragraph; Phrase

Abstract Web service discovery is a fundamental task in service-oriented architectures which searches for suitable web services based on users’ goals and preferences. In this paper, we present novel approach that can support user queries with various-size-grained text elements. Compared existing approaches only semantics matchmaking single texture granularity (either word level or paragraph level), our enables the requester to search any type of query content high performance, including word, phrase, sentence, paragraph. Specifically, an unsupervised Bayesian probabilistic model, bi-Directional Sentence-Word Topic Model (bi-SWTM), achieve semantic between possible textual types (word, paragraph) texts descriptions, by mapping words sentences same space. The bi-SWTM captures simplex, provides flexible method build links from descriptions. validated using collection comprehensive experiments ProgrammableWeb data. results demonstrate outperforms state-of-the-art methods classification. visualization nearest-neighbored descriptions shows capability model capturing latent services.