一句话：结合缺陷报告与测试执行进行故障定位并无监督融合，显著提升自动程序修复的补丁正确数。
自动程序修复的补丁质量受故障定位（FL）不精确的制约。本文首次同时利用自然语言缺陷报告与测试执行信息进行 FL 与修复。作者提出 Blues——首个基于信息检索、语句级、无需训练数据的 FL 技术，以及 RAFL——首个无监督融合多种 FL 的方法，其效果超过监督方法。将 Blues 与基于频谱的 SBFL 通过 RAFL 组合成 SBIR。在 815 个真实缺陷上，SBIR 对缺陷语句的排序始终优于其组成技术。把 Arja、SequenceR、SimFix 的内部 FL 替换为 SBIR/SBFL/Blues 并在 689 个缺陷上评估：Arja 用 SBIR 正确修复 28 个缺陷，SBFL 为 21，Blues 为 15；SequenceR 为 12/10/4；SimFix 为 30/30/13。该工作首次探索同时使用多个软件工件进行自动修复。
Automated program repair is already deployed in industry, but concerns remain about repair quality. Recent research has shown that one of the main reasons repair tools produce incorrect (but seemingly correct) patches is imperfect fault localization (FL). This paper demonstrates that combining information from natural-language bug reports and test executions when localizing faults can have a significant positive impact on repair quality. For example, existing repair tools with such FL are able to correctly repair 7 defects in the Defects4J benchmark that no prior tools have repaired correctly. We develop, Blues, the first information-retrieval-based, statement-level FL technique that requires no training data. We further develop RAFL, the first unsupervised method for combining multiple FL techniques, which outperforms a supervised method. Using RAFL, we create SBIR by combining Blues with a spectrum-based (SBFL) technique. Evaluated on 815 real-world defects, SBIR consistently ranks buggy statements higher than its underlying techniques. We then modify three state-of-the-art repair tools, Arja, SequenceR, and SimFix, to use SBIR, SBFL, and Blues as their internal FL. We evaluate the quality of the produced patches on 689 real-world defects. Arja and SequenceR significantly benefit from SBIR: Arja using SBIR correctly repairs 28 defects, but only 21 using SBFL, and only 15 using Blues; SequenceR using SBIR correctly repairs 12 defects, but only 10 using SBFL, and only 4 using Blues. SimFix, (which has internal mechanisms to overcome poor FL), correctly repairs 30 defects using SBIR and SBFL, but only 13 using Blues. Our work is the first investigation of simultaneously using multiple software artifacts for automated program repair, and our promising findings suggest future research in this directions is likely to be fruitful.