A Soft Alignment Model for Bug Deduplication

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

Bug tracking systems (BTS) are widely used in software projects. An important task in such systems consists of identifying duplicate bug reports, i.e., distinct reports related to the same software issue. For several reasons, reporting bugs that have already been reported is quite frequent, making their manual triage impractical in large BTSs. In this paper, we present a novel deep learning network based on soft-attention alignment to improve duplicate bug report detection. For a given pair of possibly duplicate reports, the attention mechanism computes interdependent representations for each report, which is more powerful than previous approaches. We evaluate our model on four well-known datasets derived from BTSs of four popular open-source projects. Our evaluation is based on a ranking-based metric, which is more realistic than decision-making metrics used in many previous works. Achieved results demonstrate that our model outperforms state-of-the-art systems and strong baselines in different scenarios. Finally, an ablation study is performed to confirm that the proposed architecture improves the duplicate bug reports detection.

Original languageEnglish
Title of host publication2020 IEEE/ACM 17th International Conference on Mining Software Repositories : MSR 2020, Proceedings; Seoul, Republic of Korea 29-30 June 2020
Number of pages11
Place of PublicationNew York
PublisherAssociation for Computing Machinery, Inc
Publication date29.06.2020
Pages43-53
ISBN (electronic)978-1-4503-7957-1
DOIs
Publication statusPublished - 29.06.2020
Externally publishedYes
Event17th IEEE/ACM International Conference on Mining Software Repositories, MSR 2020, co-located with the 42nd International Conference on Software Engineering. ICSE 2020 - Virtual, Online, Korea, Republic of
Duration: 29.06.202030.06.2020

    Research areas

  • Attention Mechanism, Bug Tracking Systems, Deep Learning, Duplicate Bug Report Detection
  • Business informatics

DOI

Recently viewed

Publications

  1. Blick über den Zaun: Leseförderung in Europa
  2. Die Tora-Mäntel der Aschkenasen in Glückstadt
  3. Survey on English Entity Linking on Wikidata
  4. Locating the Impolitical in American Theatre
  5. Versuch einer Phänomenologie des Buchstabens
  6. La leva del prezzo nel settore della cultura
  7. Biologistics and the struggle for efficiency
  8. Günter Altner - großer Kopf und freier Geist
  9. »Doch das Ding ignoriert uns und ruht in sich.«
  10. Higher Education for Sustainable Development.
  11. (Higher) Education for Sustainable Development
  12. Civil Society Responses to the HIV/AIDS Crisis
  13. Unterricht im Lernbereich Globale Entwicklung
  14. Unterricht im Lernbereich Globale Entwicklung
  15. Developing Digitalization Strategies for SMEs
  16. Bildung für nachhaltigen Konsum in der Praxis
  17. Berufsausbildung benachteiligter Jugendlicher
  18. Breast cancer survivorship symptom management
  19. Deutsch als Zweitsprache – Erwerb und Didaktik
  20. Zwischen Gesundheitsbewusstsein und Lifestyle
  21. Bildungsinstitutionen und nachhaltiger Konsum
  22. Elementarpädagogische Diskurse in Österreich
  23. Rethinking the Spatiality of Spatial Planning
  24. Historical Dictionary of Children's Literature
  25. Dadadatadada: From Dada to Data and Back Again
  26. Die Bildwelt in Walter Benjamins Kafka-Lektüre
  27. Students' conceptions about the sense of smell
  28. On the Origins of the Anthropological Machine
  29. Räume prägen Mobilität - Mobilität prägt Räume
  30. Utilising learning analytics for study success
  31. Utilities’ Business Models for Renewable Energy
  32. Review: The dark side of relict species biology
  33. Mittelschwere und schwere unipolare Depression
  34. Der Erwerb von pädagogischem Professionswissen:
  35. Ganztägige Bildung und Betreuung im Schulalter
  36. Muskelkater: Ursachen, Behandlung und Vermeidung