Machine Translation from Natural Language to Code using Long-Short Term Memory

By K. Rahit, Rashidul Hasan Nabil, Md Hasibul Huq. 2019

13 citations recorded by the source corpus.

Making computer programming language more understandable and easy for the human is a longstanding problem. From assembly language to present day's object-oriented programming, concepts came to make programming easier so that a programmer can focus on the logic and the architecture rather than the code and language itself. To go a step further in this journey of removing human-computer language barrier, this paper proposes machine learning approach using Recurrent Neural Network (RNN) and Long-Short Term Memory (LSTM) to convert human language into programming language code. The programmer will write expressions for codes in layman's language, and the machine learning model will translate it to the targeted programming language. The proposed approach yields result with 74.40% accuracy. This can be further improved by incorporating additional techniques, which are also discussed in this paper.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Brendan Dolan-Gavitt
2. Benjamin Tan
3. Foutse Khomh
4. Ramesh Karri
5. Baleegh Ahmad
6. Hammond A. Pearce
7. Michel C. Desmarais
8. Aleksander Madry

In Information Systems

1. Ramesh Karri
2. Hammond A. Pearce
3. Brendan Dolan-Gavitt
4. Benjamin Tan
5. Foutse Khomh
6. Baleegh Ahmad
7. Michel C. Desmarais

Citations in the corpus

• Asleep at the Keyboard? Assessing the Security of GitHub Copilot’s Code Contributions (2021, neutral): “There are many efforts to automatically translate specifications into computer code for natural language programming [9], through formal models for automatic code generation (e.g., [10], [11]) or via machine-learned NLP [12].”
• GitHub Copilot AI pair programmer: Asset or Liability? (2022, background): “One finds different approaches to automatic code generation in the literature, from natural language programming [23] and formal models [10, 19] to Evolutionary Algorithms [33] and machine-learned translation [28].”
• An Empirical Cybersecurity Evaluation of GitHub Copilot's Code Contributions (2021, background): “There are many efforts to automatically translate specifications into computer code for natural language programming [9], through formal models for automatic code generation (e.g., [10], [11]) or via machine-learned NLP [12].”