Abstract
Multimodal language models attempt to incorporate non-linguistic features for the language modeling task. In this work, we extend a standard recurrent neural network (RNN) language model with features derived from videos. We train our models on data that is two orders-of-magnitude bigger than datasets used in prior work. We perform a thorough exploration of model architectures for combining visual and text features. Our experiments on two corpora (YouCookII and 20bn-something-something-v2) show that the best performing architecture consists of middle fusion of visual and text features, yielding over 25% relative improvement in perplexity. We report analysis that provides insights into why our multimodal language model improves upon a standard RNN language model.
Abstract (translated by Google)
URL
http://arxiv.org/abs/1903.02930