Connecting Neural Response measurements & Computational Models of language: a non-comprehensive guide
It addresses the problem of bridging neuroscience and AI for understanding language comprehension in the brain, but as a survey, it is incremental in synthesizing existing work rather than presenting new findings.
The paper surveys the evolution of research connecting neural response measurements and computational models of language, from early studies using simple models and Event Related Potentials to contemporary approaches employing large-scale Artificial Neural Networks and multi-modal recordings with naturalistic stimuli.
Understanding the neural basis of language comprehension in the brain has been a long-standing goal of various scientific research programs. Recent advances in language modelling and in neuroimaging methodology promise potential improvements in both the investigation of language's neurobiology and in the building of better and more human-like language models. This survey traces a line from early research linking Event Related Potentials and complexity measures derived from simple language models to contemporary studies employing Artificial Neural Network models trained on large corpora in combination with neural response recordings from multiple modalities using naturalistic stimuli.