A Large-Scale Multilingual Study of Visual Constraints on Linguistic Selection of Descriptions
This work provides incremental insights into the cognitive link between vision and language, relevant for researchers in linguistics and AI language generation.
The study investigated how visual context influences linguistic choices in image captions across four languages, finding evidence that visual input constrains linguistic properties like verb transitivity and numeral use, with analysis based on 600k images and 3M captions.
We present a large, multilingual study into how vision constrains linguistic choice, covering four languages and five linguistic properties, such as verb transitivity or use of numerals. We propose a novel method that leverages existing corpora of images with captions written by native speakers, and apply it to nine corpora, comprising 600k images and 3M captions. We study the relation between visual input and linguistic choices by training classifiers to predict the probability of expressing a property from raw images, and find evidence supporting the claim that linguistic properties are constrained by visual context across languages. We complement this investigation with a corpus study, taking the test case of numerals. Specifically, we use existing annotations (number or type of objects) to investigate the effect of different visual conditions on the use of numeral expressions in captions, and show that similar patterns emerge across languages. Our methods and findings both confirm and extend existing research in the cognitive literature. We additionally discuss possible applications for language generation.