Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)

By Mariya Toneva, Leila Wehbe. Neural Information Processing Systems, 2019

312 citations recorded by the source corpus.

Neural networks models for NLP are typically implemented without the explicit encoding of language rules and yet they are able to break one performance record after another. This has generated a lot of research interest in interpreting the representations learned by these networks. We propose here a novel interpretation approach that relies on the only processing system we have that does understand language: the human brain. We use brain imaging recordings of subjects reading complex natural text to interpret word and sequence embeddings from 4 recent NLP models - ELMo, USE, BERT and Transformer-XL. We study how their representations differ across layer depth, context length, and attention type. Our results reveal differences in the context-related representations across these models. Further, in the transformer models, we find an interaction between layer depth and context length, and between layer depth and attention type. We finally hypothesize that altering BERT to better align with brain recordings would enable it to also better understand language. Probing the altered BERT using syntactic NLP tasks reveals that the model with increased brain-alignment outperforms the original model. Cognitive neuroscientists have already begun using NLP networks to study the brain, and this work closes the loop to allow the interaction between NLP and cognitive neuroscience to be a true cross-pollination.

Subfields: Artificial Intelligence, Cognitive Neuroscience

View Paper: https://www.semanticscholar.org/paper/e3567830f32444917af2d06c213435b7f1a92cd2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

Citations in the corpus

Shared computational principles for language processing in humans and deep language models (2022, result): “These results agree with concurrent studies demonstrating that contextual embeddings model neural responses to words better than static semantic embeddings 15,16,45,46 .”
Brains and algorithms partially converge in natural language processing (2022, methodology): “This result con ﬁ rms that the intermediary representations of deep language transformers are more brain-like than those of the input and output layers 33 .”
Semantic reconstruction of continuous language from non-invasive brain recordings (2022, background): “Previous studies have shown that middle layers of language models extract the best semantic features for predicting brain responses to natural language 8,14,15,17 .”