Automated labeling of bugs and tickets using attention-based mechanisms in recurrent neural networks
This work addresses the problem of automating bug and ticket labeling for software development and support teams, offering incremental improvements with new datasets and benchmarks.
The paper tackles automated labeling of bugs and tickets by classifying content based on criteria like priority or product area, presenting a hierarchical attention-based recurrent neural network that outperforms previous methods on datasets from Arch Linux and Chromium bug trackers.
We explore solutions for automated labeling of content in bug trackers and customer support systems. In order to do that, we classify content in terms of several criteria, such as priority or product area. In the first part of the paper, we provide an overview of existing methods used for text classification. These methods fall into two categories - the ones that rely on neural networks and the ones that don't. We evaluate results of several solutions of both kinds. In the second part of the paper we present our own recurrent neural network solution based on hierarchical attention paradigm. It consists of several Hierarchical Attention network blocks with varying Gated Recurrent Unit cell sizes and a complementary shallow network that goes alongside. Lastly, we evaluate above-mentioned methods when predicting fields from two datasets - Arch Linux bug tracker and Chromium bug tracker. Our contributions include a comprehensive benchmark between a variety of methods on relevant datasets; a novel solution that outperforms previous generation methods; and two new datasets that are made public for further research.