# Like a Baby: Visually Situated Neural Language Acquisition

arXiv: https://arxiv.org/abs/1805.11546 · HTML: https://mlsanity.com/paper/1805.11546/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2018.

## Built on by (most cited first, 5 of 5)

- [Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models](https://mlsanity.com/paper/2104.08066/) (2021)
- [A Computational Acquisition Model for Multimodal Word Categorization](https://mlsanity.com/paper/2205.05974/) (2022)
- [Is neural language acquisition similar to natural? A chronological probing study](https://mlsanity.com/paper/2207.00560/) (2022)
- [A Large-Scale Multilingual Study of Visual Constraints on Linguistic Selection of Descriptions](https://mlsanity.com/paper/2302.04811/) (2023)
- [Like a bilingual baby: The advantage of visually grounding a bilingual language model](https://mlsanity.com/paper/2210.05487/) (2022)

## Abstract (arXiv)

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.