Application of Seq2Seq Models on Code Correction

被引：6

作者：

Huang, Shan ^{[1
]}

Zhou, Xiao ^{[2
]}

Chin, Sang ^{[2
,3
,4
]}

机构：

[1] Boston Univ, Dept Phys, 590 Commonwealth Ave, Boston, MA 02215 USA

[2] Boston Univ, Dept Comp Sci, Boston, MA 02215 USA

[3] MIT, Dept Brain & Cognit Sci, Boston, MA USA

[4] Harvard Univ, Ctr Math Sci & Applicat, Boston, MA 02115 USA

来源：

FRONTIERS IN ARTIFICIAL INTELLIGENCE | 2021年 / 4卷

基金：

美国国家科学基金会;

关键词：

programming language correction; seq2seq architecture; pyramid encoder; attention mechanism; transfer learning;

D O I：

10.3389/frai.2021.590215

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We apply various seq2seq models on programming language correction tasks on Juliet Test Suite for C/C++ and Java of Software Assurance Reference Datasets and achieve 75% (for C/C++) and 56% (for Java) repair rates on these tasks. We introduce pyramid encoder in these seq2seq models, which significantly increases the computational efficiency and memory efficiency, while achieving similar repair rate to their nonpyramid counterparts. We successfully carry out error type classification task on ITC benchmark examples (with only 685 code instances) using transfer learning with models pretrained on Juliet Test Suite, pointing out a novel way of processing small programming language datasets.

引用

页数：13

共 33 条

[21] Short-term power load forecasting based on Seq2Seq model integrating Bayesian optimization, temporal convolutional network and attention
Dai, Yeming
Yu, Weijie
APPLIED SOFT COMPUTING, 2024, 166
[22] A Semantic-Embedding Model-Driven Seq2Seq Method for Domain-Oriented Entity Linking on Resource-Restricted Devices
Inan, Emrah
Dikenelli, Oguz
INTERNATIONAL JOURNAL ON SEMANTIC WEB AND INFORMATION SYSTEMS, 2021, 17 (03) : 73 - 87
[23] A Novel Long Short-Term Memory Seq2Seq Model with Chaos-Based Optimization and Attention Mechanism for Enhanced Dam Deformation Prediction
Wang, Lei
Wang, Jiajun
Tong, Dawei
Wang, Xiaoling
BUILDINGS, 2024, 14 (11)
[24] State-of-charge estimation hybrid method for lithium-ion batteries using BiGRU and AM co-modified Seq2Seq network and H-infinity filter
Kuang, Pan
Zhou, Fei
Xu, Shuai
Li, Kangqun
Xu, Xiaobin
ENERGY, 2024, 300
[25] Optimized EWT-Seq2Seq-LSTM with Attention Mechanism to Insulators Fault Prediction
Klaar, Anne Carolina Rodrigues
Stefenon, Stefano Frizzo
Seman, Laio Oriel
Mariani, Viviana Cocco
Coelho, Leandro dos Santos
SENSORS, 2023, 23 (06)
[26] Forcing-Seq2Seq Model: An Automatic Model of Title Generation for Natural Text Using Deep Learning
Thuan Nguyen Thi Hiep
Nhan To Thanh
Tho Quan Thanh
PROCEEDINGS OF THE FUTURE TECHNOLOGIES CONFERENCE (FTC) 2021, VOL 2, 2022, 359 : 388 - 402
[27] Wavelet-Seq2Seq-LSTM with attention for time series forecasting of level of dams in hydroelectric power plants
Stefenon, Stefano Frizzo
Seman, Laio Oriel
Aquino, Luiza Scapinello
Coelho, Leandro dos Santos
ENERGY, 2023, 274
[28] Lane Change Trajectory Prediction of Vehicles in Highway Interweaving Area Using Seq2Seq-attention Network
Han H.
Xie T.
Zhongguo Gonglu Xuebao/China Journal of Highway and Transport, 2020, 33 (06): : 106 - 118
[29] A general deep learning framework for history-dependent response prediction based on UA-Seq2Seq model
Wang, Chen
Xu, Li-yan
Fan, Jian-sheng
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2020, 372
[30] Short-time multi-energy load forecasting method based on CNN-Seq2Seq model with attention mechanism
Zhang, Ge
Bai, Xiaoqing
Wang, Yuxuan
MACHINE LEARNING WITH APPLICATIONS, 2021, 5

← 1 2 3 4 →