# Relating Simple Sentence Representations in Deep Neural Networks and the Brain

arXiv: https://arxiv.org/abs/1906.11861 · HTML: https://mlsanity.com/paper/1906.11861/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jun 2019.

## Built on by (most cited first, 10 of 10)

- [Disentangling Syntax and Semantics in the Brain with Deep Networks](https://mlsanity.com/paper/2103.01620/) (2021)
- [Joint processing of linguistic properties in brains and language models](https://mlsanity.com/paper/2212.08094/) (2022)
- [Neural Language Taskonomy: Which NLP Tasks are the most Predictive of fMRI Brain Activity?](https://mlsanity.com/paper/2205.01404/) (2022)
- [Deep Neural Networks and Brain Alignment: Brain Encoding and Decoding (Survey)](https://mlsanity.com/paper/2307.10246/) (2023)
- [Improving Semantic Understanding in Speech Language Models via Brain-tuning](https://mlsanity.com/paper/2410.09230/) (2024)
- [Speech language models lack important brain-relevant semantics](https://mlsanity.com/paper/2311.04664/) (2023)
- [The Roles of Symbols in Neural-based AI: They are Not What You Think!](https://mlsanity.com/paper/2304.13626/) (2023)
- [Divergences between Language Models and Human Brains](https://mlsanity.com/paper/2311.09308/) (2023)
- [Decoding Linguistic Representations of Human Brain](https://mlsanity.com/paper/2407.20622/) (2024)
- [Retrieving Event-related Human Brain Dynamics from Natural Sentence Reading](https://mlsanity.com/paper/2103.15500/) (2021)

## Abstract (arXiv)

What is the relationship between sentence representations learned by deep recurrent models against those encoded by the brain? Is there any correspondence between hidden layers of these recurrent models and brain regions when processing sentences? Can these deep models be used to synthesize brain data which can then be utilized in other extrinsic tasks? We investigate these questions using sentences with simple syntax and semantics (e.g., The bone was eaten by the dog.). We consider multiple neural network architectures, including recently proposed ELMo and BERT. We use magnetoencephalography (MEG) brain recording data collected from human subjects when they were reading these simple sentences. Overall, we find that BERT's activations correlate the best with MEG brain data. We also find that the deep network representation can be used to generate brain data from new sentences to augment existing brain data. To the best of our knowledge, this is the first work showing that the MEG brain recording when reading a word in a sentence can be used to distinguish earlier words in the sentence. Our exploration is also the first to use deep neural network representations to generate synthetic brain data and to show that it helps in improving subsequent stimuli decoding task accuracy.