REVISTA
AI

   
Redirigiendo al acceso original de articulo en 16 segundos...
Inicio  /  AI  /  Vol: 2 Par: 1 (2021)  /  Artículo
ARTÍCULO
TITULO

Automated Source Code Generation and Auto-Completion Using Deep Learning: Comparing and Discussing Current Language Model-Related Approaches

Juan Cruz-Benito    
Sanjay Vishwakarma    
Francisco Martin-Fernandez and Ismael Faro    

Resumen

In recent years, the use of deep learning in language models has gained much attention. Some research projects claim that they can generate text that can be interpreted as human writing, enabling new possibilities in many application areas. Among the different areas related to language processing, one of the most notable in applying this type of modeling is programming languages. For years, the machine learning community has been researching this software engineering area, pursuing goals like applying different approaches to auto-complete, generate, fix, or evaluate code programmed by humans. Considering the increasing popularity of the deep learning-enabled language models approach, we found a lack of empirical papers that compare different deep learning architectures to create and use language models based on programming code. This paper compares different neural network architectures like Average Stochastic Gradient Descent (ASGD) Weight-Dropped LSTMs (AWD-LSTMs), AWD-Quasi-Recurrent Neural Networks (QRNNs), and Transformer while using transfer learning and different forms of tokenization to see how they behave in building language models using a Python dataset for code generation and filling mask tasks. Considering the results, we discuss each approach?s different strengths and weaknesses and what gaps we found to evaluate the language models or to apply them in a real programming context.

 Artículos similares

       
 
Jan Blotnicki, Pawel Jarzembowski, Maciej Gruszczynski and Marcin Popczyk    
The application of UAV to acquire data on the morphometry of frazil ice floe in motion is demonstrated in the measurements conducted in the area of the Wroclaw Water Junction at the Opatowice weir on the Odra River (Poland). Image processing was performe... ver más
Revista: Water

 
Duc-Tien Bui, Hexuan Li, Francesco De Cristofaro and Arno Eichberger    
Lateral vehicle control is of high importance in automated vehicles as it directly influences the vehicle?s performance and safety during operation. The linear quadratic regulator (LQR) controller stands out due to its high-performance characteristics an... ver más
Revista: Applied Sciences

 
Mihai-Virgil Nichita, Maria-Alexandra Paun, Vladimir-Alexandru Paun and Viorel-Puiu Paun    
This paper introduces an AI model designed for the diagnosis and monitoring of the SARS-CoV-2 virus. The present artificial intelligence (AI) model founded on the machine learning concept was created for the identification/recognition, keeping under obse... ver más
Revista: Computers

 
Xiali Kong, Yonghua Xia, Xuequn Wu, Zhihe Wang, Kaihua Yang, Min Yan, Chen Li and Haoyu Tai    
It is fundamental to acquire accurate point cloud information on rock discontinuities efficiently and comprehensively when evaluating the stability of rock masses. Taking a high and steep cliff as an example, we combined 3D laser scanning and UAV photogr... ver más
Revista: Applied Sciences

 
Sergiu Zaharia, Traian Rebedea and Stefan Trausan-Matu    
Software developers represent the bastion of application security against the overwhelming cyber-attacks which target all organizations and affect their resilience. As security weaknesses which may be introduced during the process of code writing are com... ver más
Revista: Applied Sciences