.png){kind=icon}
.png){kind=icon}
Return
ManQ: Many-objective optimization-based automatic query reduction for IR-based bug localization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.infsof.2020.106334.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Context: An information retrieval-based bug localization (IRBL) method is proposed to localize buggy files using a bug report as a query. The performance of this method strongly depends on the quality of the query. However, these queries contain noise terms that hinder their use for IRBL. To improve the quality of a query, an automatic query reduction (AQR) technique that removes noise words from the query is needed. Objective: Our objective is to develop an AQR method for IRBL. Most existing AQR techniques are based on single objective optimization, which presents issues in terms of biased and limited performance. To solve these issues, it is necessary to find a subquery that comprehensively satisfies all of their objectives. Method: We propose an AQR technique called ManQ, which is a many-objective optimization-based AQR method for IRBL. We design 15 objective functions to (1) maintain the query quality properties, (2) maintain the important terms, (3) maintain the initial information, and (4) minimize the query length. ManQ finds a final subquery that maximize the return values of these objective functions. Results: The experimental results show that ManQ improves the quality of poor queries. We also show that if we select the best query among the candidates generated by ManQ, we can increase the number of improved queries by more than 53.4% of all queries. Conclusion: ManQ improves the performance of IRBL by improving the quality of queries through a many-objective optimization approach.
Keywords:
Bug report
Information retrieval-based bug localization
Automatic query reduction
Many-objective optimization
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.3
Papers:
3.7K
Citations:
7.7K