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
收藏
页数：13
相关论文
共 33 条
  • [1] Keyphrase Generation Based on Deep Seq2seq Model
    Zhang, Yong
    Xiao, Weidong
    IEEE ACCESS, 2018, 6 : 46047 - 46057
  • [2] SEQ2SEQ++: A Multitasking-Based Seq2seq Model to Generate Meaningful and Relevant Answers
    Palasundram, Kulothunkan
    Sharef, Nurfadhlina Mohd
    Kasmiran, Khairul Azhar
    Azman, Azreen
    IEEE ACCESS, 2021, 9 (09): : 164949 - 164975
  • [3] From Code to Natural Language: Type-Aware Sketch-Based Seq2Seq Learning
    Deng, Yuhang
    Huang, Hao
    Chen, Xu
    Liu, Zuopeng
    Wu, Sai
    Xuan, Jifeng
    Li, Zongpeng
    DATABASE SYSTEMS FOR ADVANCED APPLICATIONS (DASFAA 2020), PT I, 2020, 12112 : 352 - 368
  • [4] Reusing Monolingual Pre-Trained Models by Cross-Connecting Seq2seq Models for Machine Translation
    Oh, Jiun
    Choi, Yong-Suk
    APPLIED SCIENCES-BASEL, 2021, 11 (18):
  • [5] Laughter Synthesis: Combining Seq2seq modeling with Transfer Learning
    Tits, Noe
    El Haddad, Kevin
    Dutoit, Thierry
    INTERSPEECH 2020, 2020, : 3401 - 3405
  • [6] Knowledge-based Questions Generation with Seq2Seq Learning
    Tang, Xiangru
    Gao, Hanning
    Gao, Junjie
    PROCEEDINGS OF THE 2018 IEEE INTERNATIONAL CONFERENCE ON PROGRESS IN INFORMATICS AND COMPUTING (PIC), 2018, : 180 - 184
  • [7] Evaluating Performance of Conversational Bot Using Seq2Seq Model and Attention Mechanism
    Saluja, Karandeep
    Agrawal, Shashwat
    Kumar, Sanjeev
    Choudhury, Tanupriya
    EAI ENDORSED TRANSACTIONS ON SCALABLE INFORMATION SYSTEMS, 2024, 11 (06): : 1 - 11
  • [8] Multi-source Seq2seq guided by knowledge for Chinese healthcare consultation
    Li, Yanghui
    Wen, Guihua
    Hu, Yang
    Luo, Mingnan
    Fan, Baochao
    Wang, Changjun
    Yang, Pei
    JOURNAL OF BIOMEDICAL INFORMATICS, 2021, 117
  • [9] Anomaly-based Web Attack Detection: The Application of Deep Neural Network Seq2Seq With Attention Mechanism
    Mohammadi, Shahriar
    Namadchian, Amin
    ISECURE-ISC INTERNATIONAL JOURNAL OF INFORMATION SECURITY, 2020, 12 (01): : 44 - 54
  • [10] A Personal Conversation Assistant Based on Seq2seq with Word2vec Cognitive Map
    Shen, Maoyuan
    Huang, Runhe
    2018 7TH INTERNATIONAL CONGRESS ON ADVANCED APPLIED INFORMATICS (IIAI-AAI 2018), 2018, : 649 - 654
1234