Deep Learning Models to Study Sentence Comprehension in the Human Brain
Not on the map. Why?
Abstract (arXiv)
Recent artificial neural networks that process natural language achieve unprecedented performance in tasks requiring sentence-level understanding. As such, they could be interesting models of the integration of linguistic information in the human brain. We review works that compare these artificial language models with human brain activity and we assess the extent to which this approach has improved our understanding of the neural processes involved in natural language comprehension. Two main results emerge. First, the neural representation of word meaning aligns with the context-dependent, dense word vectors used by the artificial neural networks. Second, the processing hierarchy that emerges within artificial neural networks broadly matches the brain, but is surprisingly inconsistent across studies. We discuss current challenges in establishing artificial neural networks as process models of natural language comprehension. We suggest exploiting the highly structured representational geometry of artificial neural networks when mapping representations to brain data.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 24 of its 121 references that are in the map. First posted on arXiv 16 Jan 2023.
Builds on
24 of 121 references.
References · 24
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
- 2021Zero-Shot Text-to-Image Generationcited by 4,276
- 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,046
- 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
- 2020A Primer in BERTology: What we know about how BERT workscited by 807
- 2019Visualizing and Measuring the Geometry of BERTcited by 215
- 2019Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)cited by 128
- 2014Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathwaycited by 93
12 more
- 2019Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNscited by 90
- 2015A Primer on Neural Network Models for Natural Language Processingcited by 75
- 2022Toward a realistic model of speech processing in the brain with self-supervised learningcited by 63
- 2021Relating transformers to models and neural representations of the hippocampal formationcited by 62
- 2020Emergence of Separable Manifolds in Deep Language Representationscited by 39
- 2021Disentangling Syntax and Semantics in the Brain with Deep Networkscited by 39
- 2018Deep RNNs Encode Soft Hierarchical Syntaxcited by 34
- 2021Low-Dimensional Structure in the Space of Language Representations is Reflected in Brain Responsescited by 34
- 2021Interpreting neural computations by examining intrinsic and embedding dimensionality of neural activitycited by 24
- 2016Contextual LSTM (CLSTM) models for Large scale NLP taskscited by 15
- 2021Inductive biases, pretraining and fine-tuning jointly account for brain responses to speechcited by 14
- 2016Bridging LSTM Architecture and the Neural Dynamics during Readingcited by 4
Built on by
Citing papers per year: 2023: 1; 2024: 1; 2025: 1.
3 papers.