Diverse title generation for Stack Overflow posts with multiple-sampling-enhanced transformer

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

3 Scopus Citations
View graph of relations

Author(s)

  • Fengji Zhang
  • Jin Liu
  • Yao Wan
  • Xiao Yu
  • Xiao Liu

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article number111672
Journal / PublicationThe Journal of Systems and Software
Volume200
Online published2 Mar 2023
Publication statusPublished - Jun 2023

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. To address such a problem, we propose M3NSCT5, a novel approach to automatically generate multiple post titles from the given code snippets. Developers may take advantage of 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 with 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 applications. © 2023 Elsevier Inc. All rights reserved.

Research Area(s)

  • Stack Overflow, Title generation, CodeT5, Nucleus sampling, Maximal marginal ranking, TAG RECOMMENDATION

Citation Format(s)

Diverse title generation for Stack Overflow posts with multiple-sampling-enhanced transformer. / Zhang, Fengji; Liu, Jin; Wan, Yao et al.
In: The Journal of Systems and Software, Vol. 200, 111672, 06.2023.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review