Learning autocompletion from real-world datasets

GA Aye, S Kim, H Li - 2021 IEEE/ACM 43rd International …, 2021 - ieeexplore.ieee.org
Code completion is a popular software development tool integrated into all major IDEs.
Many neural language models have achieved promising results in completion suggestion …

When code completion fails: A case study on real-world completions

VJ Hellendoorn, S Proksch, HC Gall… - 2019 IEEE/ACM 41st …, 2019 - ieeexplore.ieee.org
Code completion is commonly used by software developers and is integrated into all major
IDE's. Good completion tools can not only save time and effort but may also help avoid …

Language models for code completion: A practical evaluation

M Izadi, J Katzy, T Van Dam, M Otten… - Proceedings of the …, 2024 - dl.acm.org
Transformer-based language models for automatic code completion have shown great
promise so far, yet the evaluation of these models rarely uses real data. This study provides …

Sequence model design for code completion in the modern IDE

GA Aye, GE Kaiser - arXiv preprint arXiv:2004.05249, 2020 - arxiv.org
Code completion plays a prominent role in modern integrated development environments
(IDEs). Machine learning has become ubiquitous in analogous natural language writing and …

A self-attentional neural architecture for code completion with multi-task learning

F Liu, G Li, B Wei, X Xia, Z Fu, Z Jin - Proceedings of the 28th …, 2020 - dl.acm.org
Code completion, one of the most useful features in the Integrated Development
Environments (IDEs), can accelerate software development by suggesting the libraries …

Towards full-line code completion with neural language models

W Wang, S Shen, G Li, Z Jin - arXiv preprint arXiv:2009.08603, 2020 - arxiv.org
A code completion system suggests future code elements to developers given a partially-
complete code snippet. Code completion is one of the most useful features in Integrated …

When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference

Z Sun, X Du, F Song, S Wang, L Li - Proceedings of the IEEE/ACM 46th …, 2024 - dl.acm.org
Leveraging recent advancements in large language models, modern neural code
completion models have demonstrated the capability to generate highly accurate code …

Combining program analysis and statistical language model for code statement completion

S Nguyen, T Nguyen, Y Li… - 2019 34th IEEE/ACM …, 2019 - ieeexplore.ieee.org
Automatic code completion helps improve developers' productivity in their programming
tasks. A program contains instructions expressed via code statements, which are considered …

Reacc: A retrieval-augmented code completion framework

S Lu, N Duan, H Han, D Guo, S Hwang… - arXiv preprint arXiv …, 2022 - arxiv.org
Code completion, which aims to predict the following code token (s) according to the code
context, can improve the productivity of software development. Recent work has proved that …

Multi-task learning based pre-trained language model for code completion

F Liu, G Li, Y Zhao, Z Jin - Proceedings of the 35th IEEE/ACM …, 2020 - dl.acm.org
Code completion is one of the most useful features in the Integrated Development
Environments (IDEs), which can accelerate software development by suggesting the next …