Learning Visually Grounded Sentence Representations

AbstractWe investigate grounded sentence representations, where we train a sentence encoder to predict the image features of a given caption—i.e., we try to “imagine” how a sentence would be depicted visually—and use the resultant features as sentence representations. We examine the quality of the learned representations on a variety of standard sentence representation quality benchmarks, showing improved performance for grounded models over non-grounded ones. In addition, we thoroughly analyze the extent to which grounding contributes to improved performance, and show that the system also learns improved word embeddings.