[Submitted on 29 May 2018 (v1), last revised 24 Jul 2026 (this version, v3)]

View PDF HTML (experimental)

Abstract:We examine the benefits of visual context in training neural language models to perform next-word prediction. A multi-modal neural architecture is introduced that outperform its equivalent trained on language alone with a 2% decrease in perplexity, even when no visual context is available at test. Fine-tuning the embeddings of a pre-trained state-of-the-art bidirectional language model (BERT) in the language modeling framework yields a 3.5% improvement. The advantage for training with visual context when testing without is robust across different languages (English, German and Spanish) and different models (GRU, LSTM, $\Delta$-RNN, as well as those that use BERT embeddings). Thus, language models perform better when they learn like a baby, i.e, in a multi-modal environment. This finding is compatible with the theory of situated cognition: language is inseparable from its physical context.

Submission history

From: Mary Alexandria Kelly [view email]
[v1] Tue, 29 May 2018 15:53:30 UTC (650 KB)
[v2] Tue, 4 Jun 2019 05:11:20 UTC (802 KB)
[v3] Fri, 24 Jul 2026 21:43:42 UTC (823 KB)