Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
Automated Program Repair using Pre-trained Model for Programming Languages |
¿µ¹®Á¦¸ñ(English Title) |
Automated Program Repair using Pre-trained Model for Programming Languages |
ÀúÀÚ(Author) |
Aditi
Su-Hyeon Kim
Hyeon-Tae Seo
Sang-Ki Ko
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 49 NO. 02 PP. 1682 ~ 1684 (2022. 12) |
Çѱ۳»¿ë (Korean Abstract) |
|
¿µ¹®³»¿ë (English Abstract) |
The problem of automatically fixing programming errors is an emerging topic in the field of software engineering. Fixing errors in the code is a challenging problem, as a simple error may require syntactic and semantic analysis of the entire program to fix the error. These errors occur mostly due to the lack of the programmer¡¯s attention and concentration while programming. Recently, many researchers have proposed various deep learning-based solutions by teaching neural networks how to fix given erroneous source codes from numerous source codes publicly available. In this work, we present a deep learning-based solution for automatically fixing given C programs using a pre-trained model for programming language, CodeBERT. We evaluate our method with the publicly available dataset (DeepFix dataset) that consists of erroneous C programs submitted by novice programming students. |
Å°¿öµå(Keyword) |
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|