There is a growing consensus that surface form alone does not enable models to learn meaning and gain language understanding. This warrants an interest in hybrid systems that combine the strengths of neural and symbolic methods. We favour triadic systems consisting of neural networks, knowledge bases, and inference engines. The network provides perception, that is, the interface between the system and its environment. The knowledge base provides explicit memory and thus immediate access to established facts. Finally, inference capabilities are provided by the inference engine which reflects on the perception, supported by memory, to reason and discover new facts. In this work, we probe six popular language models for semantic relations and outline a future line of research to study how the constituent subsystems can be jointly realised and integrated.

Semantic embeddings have advanced the state of the art for countless natural language processing tasks, and various extensions to multimodal domains, such as visual-semantic embeddings, have been proposed. While the power of visual-semantic embeddings comes from the distillation and enrichment of information through machine learning, their inner workings are poorly understood and there is a shortage of analysis tools. To address this problem, we generalize the notion ofprobing tasks to the visual-semantic case. To this end, we (i) discuss the formalization of probing tasks for embeddings of image-caption pairs, (ii) define three concrete probing tasks within our general framework, (iii) train classifiers to probe for those properties, and (iv) compare various state-of-the-art embeddings under the lens of the proposed probing tasks. Our experiments reveal an up to 16% increase in accuracy on visual-semantic embeddings compared to the corresponding unimodal embeddings, which suggest that the text and image dimensions represented in the former do complement each other.