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 M3NSCT5, 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. M3NSCT5 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 M3NSCT5. The automatic evaluation results on the BLEU and ROUGE metrics demonstrate the superiority of M3NSCT5 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.
Cite
@article{arxiv.2208.11523,
title = {Diverse Title Generation for Stack Overflow Posts with Multiple Sampling Enhanced Transformer},
author = {Fengji Zhang and Jin Liu and Yao Wan and Xiao Yu and Xiao Liu and Jacky Keung},
journal= {arXiv preprint arXiv:2208.11523},
year = {2023}
}