SERNOTATE: An automated approach for business service description annotation for efficient service retrieval and composition
- Publication Type:
- Journal Article
- Citation:
- Concurrency Computation, 2018, 30 (1)
- Issue Date:
- 2018-01-10
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| Chotipant_et_al-2018-Concurrency_and_Computation%3A_Practice_and_Experience.pdf | Published Version | 5.33 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Copyright © 2017 John Wiley & Sons, Ltd. Business service advertisements are today published online to convey essential information about services to customers. However, current Web search engines are unable to search and combine online service advertisements. Semantic service annotation is important for its ability to enable machines to understand the meaning of services and support in effective service retrieval and service composition. Existing research in the area of semantic service annotation has focused on the annotation of Web services in a semi-automated approach. It cannot be applied to business service information as it is not in the form of Web Services Description Language but in free text format. Moreover, semi-automated approaches are inappropriate for annotating a large amount of online service information which changes dynamically and they are therefore not suitable for the timely dissemination of service information to customers. To solve these issues, we propose SERNOTATE, which is an automated approach for business service description annotation for efficient service retrieval and composition. We propose new semantic-based linking approaches, namely, Extended Case-based Reasoning, vector-based, and classification-based, that automatically annotate business services to relevant service concepts. Each approach assists in the single-label and multi-label annotation of service terms to concept terms to provide a better representation of services. The experimental results test and validate the applicability of the proposed approaches to the automatic annotation of business service descriptions to service concepts on a real-world dataset.
Please use this identifier to cite or link to this item: