Diverse Title Generation for Stack Overflow Posts with Multiple Sampling Enhanced Transformer

TL;DR

This paper introduces M3NSCT5, a Transformer-based method that generates diverse, high-quality titles for Stack Overflow posts from code snippets, aiding developers in better problem description and retrieval.

Contribution

It proposes a novel maximal marginal multiple nucleus sampling strategy and a large-scale dataset, improving title diversity and quality over existing models.

Findings

M3NSCT5 outperforms six baseline models on BLEU and ROUGE metrics.

Human evaluation confirms the quality and diversity of generated titles.

The approach demonstrates potential for real-world application in programming communities.

Abstract

Stack Overflow is one of the most popular programming communities where developers can seek help for their encountered problems. Nevertheless, if inexperienced developers fail to describe their problems clearly, it is hard for them to attract sufficient attention and get the anticipated answers. We propose M$_3$NSCT5, a novel approach to automatically generate multiple post titles from the given code snippets. Developers may use the generated titles to find closely related posts and complete their problem descriptions. M$_3$NSCT5 employs the CodeT5 backbone, which is a pre-trained Transformer model having an excellent language understanding and generation ability. To alleviate the ambiguity issue that the same code snippets could be aligned with different titles under varying contexts, we propose the maximal marginal multiple nucleus sampling strategy to generate multiple high-quality and diverse title candidates at a time for the developers to choose from. We build a large-scale dataset with 890,000 question posts covering eight programming languages to validate the effectiveness of M$_3$NSCT5. The automatic evaluation results on the BLEU and ROUGE metrics demonstrate the superiority of M$_3$NSCT5 over six state-of-the-art baseline models. Moreover, a human evaluation with trustworthy results also demonstrates the great potential of our approach for real-world application.