Understanding and manipulating concrete and abstract concepts is fundamental to human intelligence. Yet, they remain challenging for artificial agents. This paper introduces a multimodal generative approach to high order abstract concept learning, which integrates visual and categorical linguistic information from concrete ones. Our model initially grounds subordinate level concrete concepts, combines them to form basic level concepts, and finally abstracts to superordinate level concepts via the grounding of basic-level concepts. We evaluate the model language learning ability through language-to-visual and visual-to-language tests with high order abstract concepts. Experimental results demonstrate the proficiency of the model in both language understanding and language naming tasks.

The "basic level", according to experiments in cognitive psychology, is the level of abstraction in a hierarchy of concepts at which humans perform tasks quicker and with greater accuracy than at other levels. We argue that applications that use concept hierarchies - such as knowledge graphs, ontologies or taxonomies - could significantly improve their user interfaces if they `knew' which concepts are the basic level concepts. This paper examines to what extent the basic level can be learned from data. We test the utility of three types of concept features, that were inspired by the basic level theory: lexical features, structural features and frequency features. We evaluate our approach on WordNet, and create a training set of manually labelled examples that includes concepts from different domains. Our findings include that the basic level concepts can be accurately identified within one domain. Concepts that are difficult to label for humans are also harder to classify automatically. Our experiments provide insight into how classification performance across domains could be improved, which is necessary for identification of basic level concepts on a larger scale.