The Use of Natural Language Processing Approach for Converting Pseudo Code to C# Code

• Main Authors: Imam Ayad Tareq, Alnsour Ayman Jameel
• Format: Article
• Language: English
• Published: De Gruyter 2019-04-01
• Series: Journal of Intelligent Systems
• Subjects: acg; i-case; nlp; srl; thematic role; verb classification
• Online Access: https://doi.org/10.1515/jisys-2018-0291

Although current computer-aided software engineering tools support developers in composing a program, there is no doubt that more flexible supportive tools are needed to address the increases in the complexity of programs. This need can be met by automating the intellectual activities that are carried out by humans when composing a program. This paper aims to automate the composition of a programming language code from pseudocode, which is viewed here as a translation process for a natural language text, as pseudocode is a formatted text in natural English language. Based on this view, a new automatic code generator is developed that can convert pseudocode to C# programming language code. This new automatic code generator (ACG), which is called CodeComposer, uses natural language processing (NLP) techniques such as verb classification, thematic roles, and semantic role labeling (SRL) to analyze the pseudocode. The resulting analysis of linguistic information from these techniques is used by a semantic rule-based mapping machine to perform the composition process. CodeComposer can be viewed as an intelligent computer-aided software engineering (I_CASE) tool. An evaluation of the accuracy of CodeComposer using a binomial technique shows that it has a precision of 88%, a recall of 91%, and an F-measure of 89%.