Context Composing for Full Line Code Completion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910331290255360 |
|---|---|
| author | Semenkin, Anton Sokolov, Yaroslav Vu, Evgeniia |
| author_facet | Semenkin, Anton Sokolov, Yaroslav Vu, Evgeniia |
| contents | Code Completion is one of the most used Integrated Development Environment (IDE) features, which affects the everyday life of a software developer. Modern code completion approaches moved from the composition of several static analysis-based contributors to pipelines that involve neural networks. This change allows the proposal of longer code suggestions while maintaining the relatively short time spent on generation itself. At JetBrains, we put a lot of effort into perfecting the code completion workflow so it can be both helpful and non-distracting for a programmer. We managed to ship the Full Line Code Completion feature to PyCharm Pro IDE and proved its usefulness in A/B testing on hundreds of real Python users. The paper describes our approach to context composing for the Transformer model that is a core of the feature's implementation. In addition to that, we share our next steps to improve the feature and emphasize the importance of several research aspects in the area. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09230 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Context Composing for Full Line Code Completion Semenkin, Anton Sokolov, Yaroslav Vu, Evgeniia Software Engineering Machine Learning Code Completion is one of the most used Integrated Development Environment (IDE) features, which affects the everyday life of a software developer. Modern code completion approaches moved from the composition of several static analysis-based contributors to pipelines that involve neural networks. This change allows the proposal of longer code suggestions while maintaining the relatively short time spent on generation itself. At JetBrains, we put a lot of effort into perfecting the code completion workflow so it can be both helpful and non-distracting for a programmer. We managed to ship the Full Line Code Completion feature to PyCharm Pro IDE and proved its usefulness in A/B testing on hundreds of real Python users. The paper describes our approach to context composing for the Transformer model that is a core of the feature's implementation. In addition to that, we share our next steps to improve the feature and emphasize the importance of several research aspects in the area. |
| title | Context Composing for Full Line Code Completion |
| topic | Software Engineering Machine Learning |
| url | https://arxiv.org/abs/2402.09230 |