Abstract | ||
---|---|---|
Web service composition can provide value-added services and can satisfy consumers with complex functionality. In Web service composition, the common method is to collect suitable services from a large Web service repository and assemble them based on some rules or knowledge. However, the procedures require heavy data processing and manual work, Web service composition is still a complex task in automatic service composition. And these service composition sequences are a kind of abstract data. So, it is significant to find a method that we can extract some useful information or knowledge from these abstract sequences and apply them in Web service composition. In this study, we propose Web service composition sequence learning to construct a circular framework in Web service discovery. This method aims to learn the invocation relevance between services from the service composition sequences and use them to contribute to other nodes in the framework. Then, we adopt neural language networks to perform Web service composition sequence learning. The experimental results show that our models can learn Web service composition well and that the representative vectors generated by the pretrained model can be utilized to implement related service discovery. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/BigDataSE50710.2020.00008 | 2020 IEEE 14th International Conference on Big Data Science and Engineering (BigDataSE) |
Keywords | DocType | ISBN |
Web service composition,deep learning,API sequence,RNN,BERT | Conference | 978-1-6654-0397-9 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kungan Zeng | 1 | 0 | 0.34 |
Incheon Paik | 2 | 241 | 38.80 |