Compositional Vector Space Models for Improved Bug Localization

Abstract

Software developers and maintainers often need to locate code units responsible for a particular bug. A number of Information Retrieval (IR) techniques have been proposed to map natural language bug descriptions to the associated code units. The vector space model (VSM) with the standard tf-idf weighting scheme (VSM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">natural</sub> ), has been shown to outperform nine other state-of-the-art IR techniques. However, there are multiple VSM variants with different weighting schemes, and their relative performance differs for different software systems. Based on this observation, we propose to compose various VSM variants, modelling their composition as an optimization problem. We propose a genetic algorithm (GA) based approach to explore the space of possible compositions and output a heuristically near-optimal composite model. We have evaluated our approach against several baselines on thousands of bug reports from AspectJ, Eclipse, and SWT. On average, our approach (VSM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">composite</sub> ) improves hit at 5 (Hit@5), mean average precision (MAP), and mean reciprocal rank (MRR) scores of VSM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">natural</sub> by 18.4%, 20.6%, and 10.5% respectively. We also integrate our compositional model with AmaLgam, which is a state-of-art bug localization technique. The resultant model named AmaLgam <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">composite</sub> on average can improve Hit@5, MAP, and MRR scores of AmaLgam by 8.0%, 14.4% and 6.5% respectively.