Good things come in three: Generating SO Post Titles with Pre-Trained Models, Self Improvement and Post Ranking

June 21, 2024 Β· Declared Dead Β· πŸ› International Symposium on Empirical Software Engineering and Measurement

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Duc Anh Le, Anh M. T. Bui, Phuong T. Nguyen, Davide Di Ruscio arXiv ID 2406.15633 Category cs.SE: Software Engineering Citations 1 Venue International Symposium on Empirical Software Engineering and Measurement Last Checked 5 months ago
Abstract
Stack Overflow is a prominent Q and A forum, supporting developers in seeking suitable resources on programming-related matters. Having high-quality question titles is an effective means to attract developers' attention. Unfortunately, this is often underestimated, leaving room for improvement. Research has been conducted, predominantly leveraging pre-trained models to generate titles from code snippets and problem descriptions. Yet, getting high-quality titles is still a challenging task, attributed to both the quality of the input data (e.g., containing noise and ambiguity) and inherent constraints in sequence generation models. In this paper, we present FILLER as a solution to generating Stack Overflow post titles using a fine-tuned language model with self-improvement and post ranking. Our study focuses on enhancing pre-trained language models for generating titles for Stack Overflow posts, employing a training and subsequent fine-tuning paradigm for these models. To this end, we integrate the model's predictions into the training process, enabling it to learn from its errors, thereby lessening the effects of exposure bias. Moreover, we apply a post-ranking method to produce a variety of sample candidates, subsequently selecting the most suitable one. To evaluate FILLER, we perform experiments using benchmark datasets, and the empirical findings indicate that our model provides high-quality recommendations. Moreover, it significantly outperforms all the baselines, including Code2Que, SOTitle, CCBERT, M3NSCT5, and GPT3.5-turbo. A user study also shows that FILLER provides more relevant titles, with respect to SOTitle and GPT3.5-turbo.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Software Engineering

Died the same way β€” πŸ‘» Ghosted