Illustrative Language Understanding: Large-Scale Visual Grounding with Image Search

Jamie Kiros, William Chan, Geoffrey Hinton

We introduce Picturebook, a large-scale lookup operation to ground language via `snapshots' of our physical world accessed through image search. For each word in a vocabulary, we extract the top-$k$ images from Google image search and feed the images through a convolutional network to extract a word embedding. We introduce a multimodal gating function to fuse our Picturebook embeddings with other word representations. We also introduce Inverse Picturebook, a mechanism to map a Picturebook embedding back into words. We experiment and report results across a wide range of tasks: word similarity, natural language inference, semantic relatedness, sentiment/topic classification, image-sentence ranking and machine translation. We also show that gate activations corresponding to Picturebook embeddings are highly correlated to human judgments of concreteness ratings.