概要: The object of this study is Docker, the de facto standard containerization platform. Containers in Docker are built by creating files called Dockerfiles. Managing the infrastructure as code makes it possible to incorporate knowledge gained from conventional software development. However, infrastructure as code is a relatively new technology, some domains of which have not been fully researched. In this study, we focus on code completion and aim to construct a system that supports the development of Dockerfiles. The proposed code completion system, Humpback, applies machine learning to a pre-collected dataset with long short-term memory to create language models and uses model switching to overcome a Docker-specific code completion problem. Evaluation experiments show that Humpback has a high average accuracy of 96.9%. タグ: code, completion, dockerfiles, humpback, language, models, system

@inproceedings{KaiseiHanayama2020,
  author = {Kaisei Hanayama and Shinsuke Matsumoto and Shinji Kusumoto},
  title = {Humpback: Code Completion System for Dockerfiles Based on Language Models},
  booktitle = {1st Workshop on Natural Language Processing Advancements for Software Engineering (NLPaSE 2020)},
  pages = {1--4},
  year = {2020},
  month = {dec}
}