pith. sign in

arxiv: 1903.02930 · v1 · pith:GJ4PHVIFnew · submitted 2019-03-07 · 💻 cs.CL

Neural Language Modeling with Visual Features

classification 💻 cs.CL
keywords languagefeaturesmodelvisualmodelingmodelsmultimodalneural
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.