Neural Language Modeling with Visual Features
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 datase...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | 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. |
---|---|
DOI: | 10.48550/arxiv.1903.02930 |