From distributional semantics to feature norms: grounding semantic models in human perceptual data
Luana Fagarasan, Eva Maria Vecchi, Stephen Charles Clark · 2015
Multimodal semantic models attempt to ground distributional semantics through the integration of visual or perceptual information. Feature norms provide useful insight into human concept acquisition, but cannot be used to ground large-scale semantics because they are expensive to produce. We present an automatic method for predicting feature norms for new concepts by learning a mapping from a text-based distributional semantic space to a space built using feature norms. Our experimental results show that we are able to generalise feature-based concept representations, which opens up the possibility of developing large-scale semantic models grounded in a proxy for human perceptual data.