Automating smart recommendation from natural language API descriptions via representation learning

摘要

Software reuse through Application Programming Interfaces (APIs) is a common practice in software development. It remains a big challenge to bridge the semantic gap between user requirements and application functionality with the development of Web-based services. This paper proposes a smart service recommendation approach via Representation Learning. To validate our approach, large-scale experiments are conducted based on a real-world accessible service repository, Programmable-Web. The results show the effectiveness of our proposed approach. (C) 2018 Elsevier B.V. All rights reserved.