Site Reliability Engineers (SREs) play a key role in identifying the cause of an issue and preforming remediation steps to resolve it. After an issue is reported, SREs come together in a virtual room (collaboration platform) to triage the issue. While doing so, they leave behind a wealth of information, in the form of conversations, which can be used later for triaging similar issues. However, usability of these conversations offer challenges due to them being and scarcity of conversation utterance label. This paper presents a novel approach for issue artefact extraction from noisy conversations with minimal labelled data. We propose a combination of unsupervised and supervised models with minimal human intervention that leverages domain knowledge to predict artefacts for a small amount of conversation data and use that for fine-tuning an already pre-trained language model for artefact prediction on a large amount of conversation data. Experimental results on our dataset show that the proposed ensemble of the unsupervised and supervised models is better than using either one of them individually. We also present a deployment case study of the proposed artefact prediction.

Crowdsourcing in the form of human-based electronic services (people services) provides a powerful way of outsourcing tasks to a large crowd of remote workers over the Internet. Research has shown that multiple redundant results delivered by different workers can be aggregated in order to achieve a reliable result. However, basic implementations of this approach are rather inefficient as they multiply the effort for task execution and are not able to guarantee a certain quality level. In this paper, we are addressing these challenges by elaborating on a statistical approach for quality management of people services which we had previously proposed. The approach combines elements of statistical quality management with dynamic group decisions. We present a comprehensive statistical model that enhances our original work and makes it more transparent. We also provide an extendible toolkit that implements our model and facilitates its application to real-time experiments as well as to simulations. A quantitative analysis based on an optical character recognition (OCR) scenario confirms the efficiency and reach of our model.