Current statistical language modeling techniques, including deep-learning based models, have proven to be quite effective for source code. We argue here that the special properties …
The usage of deep learning (DL) approaches for software engineering has attracted much attention, particularly in source code modelling and analysis. However, in order to use DL …
C Niu, C Li, V Ng, D Chen, J Ge… - 2023 IEEE/ACM 45th …, 2023 - ieeexplore.ieee.org
While a large number of pre-trained models of source code have been successfully developed and applied to a variety of software engineering (SE) tasks in recent years, our …
D Wang, Z Jia, S Li, Y Yu, Y Xiong, W Dong… - Proceedings of the 44th …, 2022 - dl.acm.org
With the great success of pre-trained models, the pretrain-then-finetune paradigm has been widely adopted on downstream tasks for source code understanding. However, compared to …
Y Hussain, Z Huang, Y Zhou, S Wang - International Journal of …, 2020 - World Scientific
In recent years, deep learning models have shown great potential in source code modeling and analysis. Generally, deep learning-based approaches are problem-specific and data …
In 2006, Geoffrey Hinton proposed the concept of training “Deep Neural Networks (DNNs)” and an improved model training method to break the bottleneck of neural network …
An increasingly popular set of techniques adopted by software engineering (SE) researchers to automate development tasks are those rooted in the concept of Deep …
The growing cost of deep learning for source code Page 1 JANUARY 2022 | VOL. 65 | NO. 1 | COMMUNICATIONS OF THE ACM 31 viewpoints IMA GER YB Y OZZ DE SIGN uniquely …
There has been a recent surge of interest in automating software engineering tasks using deep learning. This article addresses the problem of code generation, in which the goal is to …