papers AI Learner
The Github is limit! Click to go to the new site.

Neural Language Modeling with Visual Features

2019-03-07
Antonios Anastasopoulos, Shankar Kumar, Hank Liao

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

PDF

http://arxiv.org/pdf/1903.02930


Comments

Content