Text2PyCode: Machine Translation of Natural Language Intent to Python']Python Source Code

被引：1

作者：

Bonthu, Sridevi ^{[1
,3
]}

Sree, S. Rama ^{[2
]}

Prasad, M. H. M. Krishna ^{[3
]}

机构：

[1] Vishnu Inst Technol, Bhimavaram, Andhra Pradesh, India

[2] Aditya Engn Coll, Surampalem, Andhra Pradesh, India

[3] Jawaharlal Nehru Technol Univ, Kakinada, Andhra Pradesh, India

来源：

MACHINE LEARNING AND KNOWLEDGE EXTRACTION (CD-MAKE 2021) | 2021年 / 12844卷

关键词：

Deep learning; Attention; Transformer; Code generation; !text type='Python']Python[!/text; Neural machine translation;

D O I：

10.1007/978-3-030-84060-0_4

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Natural Language Processing has improved tremendously with the success of Deep Learning. Neural Machine Translation (NMT) has arisen as the most powerful with the power of Deep Learning. The same idea has been recently applied to source code. Code Generation (CG) is the task of generating source code from natural language input. This paper introduces a Python parallel corpus of natural language intent and source code pairs. It also proposes a Code Generation model based on Transformer architecture used for NMT by using code tokenization and code embeddings on the custom parallel corpus. The proposed architecture achieved a good BLEU score of 32.4 and Rouge-L of 82.1, which is on par with natural language translation.

引用

页码：51 / 60

页数：10

共 19 条

[1] Natural Language to Python Source Code using Transformers
Shah, Meet
Shenoy, Rajat
Shankarmani, Radha
2021 International Conference on Intelligent Technologies, CONIT 2021, 2021,
[2] PYMT5: multi-mode translation of natural language and PYTHON']PYTHON code with transformers
Clement, Colin B.
Drain, Dawn
Timcheck, Jonathan
Svyatkovskiy, Alexey
Sundaresan, Neel
PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 9052 - 9065
[3] Machine Learning Techniques For Python']Python Source Code Vulnerability Detection
Farasat, Talaya
Posegga, Joachim
PROCEEDINGS OF THE FOURTEENTH ACM CONFERENCE ON DATA AND APPLICATION SECURITY AND PRIVACY, CODASPY 2024, 2024, : 151 - 153
[4] Transformers based Python']Python Code Generation from Natural Language
Swathi, Smt E.
Vanga, Abhinav Reddy
2024 5TH INTERNATIONAL CONFERENCE ON INNOVATIVE TRENDS IN INFORMATION TECHNOLOGY, ICITIIT 2024, 2024,
[5] PyMLDA: A Python']Python open-source code for Machine Learning Damage Assessment
Coelho, Jefferson da Silva
Machado, Marcela Rodrigues
de Sousa, Amanda Aryda S. R.
SOFTWARE IMPACTS, 2024, 19
[6] Is the Corpus Ready for Machine Translation? A Case Study with Python']Python to Pseudo-Code Corpus
Rai, Sawan
Belwal, Ramesh Chandra
Gupta, Atul
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING, 2023, 48 (02) : 1845 - 1858
[7] CAMeL Tools: An Open Source Python']Python Toolkit for Arabic Natural Language Processing
Obeid, Ossama
Zalmout, Nasser
Khalifa, Salam
Taji, Dima
Oudah, Mai
Alhafni, Bashar
Inoue, Go
Eryani, Fadhl
Erdmann, Alexander
Habash, Nizar
PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2020), 2020, : 7022 - 7032
[8] Code2graph: Automatic Generation of Static Call Graphs for Python']Python Source Code
Gharibi, Gharib
Tripathi, Rashmi
Lee, Yugyung
PROCEEDINGS OF THE 2018 33RD IEEE/ACM INTERNATIONAL CONFERENCE ON AUTOMTED SOFTWARE ENGINEERING (ASE' 18), 2018, : 880 - 883
[9] Seq2Code: Transformer-Based Encoder-Decoder Model for Python']Python Source Code Generation
Laskari, Naveen Kumar
Reddy, K. Adi Narayana
Reddy, M. Indrasena
THIRD CONGRESS ON INTELLIGENT SYSTEMS, CIS 2022, VOL 1, 2023, 608 : 301 - 309
[10] Is the Corpus Ready for Machine Translation? A Case Study with Python to Pseudo-Code Corpus
Sawan Rai
Ramesh Chandra Belwal
Atul Gupta
Arabian Journal for Science and Engineering, 2023, 48 : 1845 - 1858

← 1 2 →