Automated Test Case Generation Using T5 and GPT-3
Alok Mathur, Shreyaan Pradhan, Prasoon Soni, Dhruvil Patel, Rajeshkannan Regunathan
Abstract
Test case generation for a given topic can be a challenging and time-consuming task, particularly when the conversation about the topic includes boundary conditions and requirements. This process requires a complete understanding of the system and its scenarios to cover all possible examples, both good and bad. This paper proposes an automated solution for generating test cases using natural language processing techniques. The proposed methodology uses T5 and GPT-3 models to extract the context and topic of the conversation and generate test cases. The model identifies relevant keywords and generates test cases based on them, providing context-based meanings of specific words and defining new terms used in the conversation. The proposed approach eliminates the need for manual test case generation and allows for the testing of more complex systems with a larger number of scenarios. This will reduce the dependency on the expertise of the test designer, resulting in complete coverage of all scenarios. Additionally, this automation will save time and resources, making the process of test case generation more manageable. By utilizing NLP techniques, it will help to ensure that all scenarios are taken into account and that the test cases generated are comprehensive and accurate.