Made of Steel? Learning Plausible Materials for Components in the Vehicle Repair Domain

We propose a novel approach to learn domainspecific plausible materials for components in the vehicle repair domain by probing Pretrained Language Models (PLMs) in a cloze task style setting to overcome the lack of annotated datasets. We devise a new method to aggregate salient predictions from a set of cloze query templates and show that domainadaptation using either a small, high-quality or a customized Wikipedia corpus boosts performance. When exploring resource-lean alternatives, we find a distilled PLM clearly outperforming Figure 1: Conceptual overview for learning domainspecific a classic pattern-based algorithm. Further, plausible materials (e.g., aluminium) for vehicle given that 98% of our domain-specific components (e.g., engine valves rocker arm).