Comparative Study of LSTM and T5-Flan Models for Automated Test Case Generation from Gherkin Requirements
Project by Polygence alum Sree harshini
Project's result
Working models for both the LSTM and T5-Flan models (trained from scratch) along with a research paper.
They started it from zero. Are you ready to level up with us?
Summary
This paper investigates the application of LSTM and T5-Flan models for generating test cases from simplified Gherkin requirements in automated software testing. Automated test case generation using AI models has gained prominence recently, offering substantial benefits in efficiency and reliability. Therefore, understanding the comparative strengths of different models in this domain is helpful for optimizing software testing practices.In this study, we compare and analyze the performance of both models in terms of accuracy and efficiency, using a diverse dataset of Gherkin scenarios and evaluation metrics such as BLEU, ROGUE, BERTScore, and Semantic Similarity. The findings demonstrate that T5-Flan consistently outperforms LSTM across all metrics, showcasing superior capability in capturing complex dependencies and semantic nuances present in Gherkin requirements.
Mohith
Polygence mentor
MS Master of Science
Subjects
Business, Engineering, Quantitative, Computer Science
Expertise
Business, Econ, App development, Web Development, AI/ML Algorithm development, other Computer Science areas, High School subjects
Check out their profile
Sree harshini
Student
Hello my name is Sree harshini (but everyone just calls me Sree) and my project is a Comparative Study of LSTM and T5-Flan Models for Automated Test Case Generation.
Graduation Year
2025
Project review
“My project taught me a lot about a field I never thought I could understand. I truly learned a lot and now feel more confident about myself and my major.”
About my mentor
“Mohith was very chill and fun to work with :) He kept the project proceeding smoothly and helped me a lot whenever I needed it.”
Check out their profile