Towards Generating Colour Terms for Referents in Photographs: Prefer the Expected or the Unexpected?

Colour terms have been a prime phenomenon for studying language grounding, though previous work focussed mostly on descriptions of simple objects or colour swatches. This paper investigates whether colour terms can be learned from more realistic and potentially noisy visual inputs, using a corpus of referring expressions to objects represented as regions in real-world images. We obtain promising results from combining a classifier that grounds colour terms in visual input with a recalibration model that adjusts probability distributions over colour terms according to contextual and object-specific preferences.