Finding the appropriate developer for a bug report, so called `Bug Triage', is one of the bottlenecks in the bug resolution process. To address this problem, many approaches have proposed various automatic bug triage techniques in recent studies. We argue that most previous studies focused on open source projects only and did not consider deep learning techniques. In this paper, we propose to use Convolutional Neural Network and word embedding to build an automatic bug triager. The results of the experiments applied to both industrial and open source projects reveal benefits of the automatic approach and suggest co-operation of human and automatic triagers. Our experience in integrating and operating the proposed system in an industrial development environment is also reported.

bug report is typically assigned to a single developer who is then responsible for fixing the bug. In Mozilla and Eclipse, between 37%-44% of bug reports are "tossed" (reassigned) to other developers, for example because the bug has been assigned by accident or another developer with additional expertise is needed. In any case, tossing increases the time-to-correction for a bug.