Modelling Form-Meaning Systematicity with Linguistic and Visual Features

Several studies in linguistics and natural language processing (NLP) pointed out systematic correspondences between word form and meaning in language. A prominent example of such systematicity is iconicity, which occurs when the form of a word is motivated by some perceptual (e.g. visual) aspect of its referent. However, the existing data-driven approaches to form-meaning systematicity modelled word meanings relying on information extracted from textual data alone. In this paper, we investigate to what extent our visual experience explains some of the form-meaning systematicity found in language. We construct word meaning representations from linguistic as well as visual data and analyze the structure and significance of form-meaning systematicity found in English using these models. Our findings corroborate the existence of form-meaning systematicity and show that this systematicity is concentrated in localized clusters. Furthermore, applying a multimodal approach allows us to identify new patterns of systematicity that have not been previously identified with the text-based models.