Bridging Language in Machines with Language in the Brain - Speaker: Mariya Toneva
In this talk, I’ll discuss a data-driven framework that circumvents these limitations by establishing a direct connection between brain recordings of people comprehending language and natural language processing (NLP) computer systems. I’ll present evidence that this connection can be beneficial for both neurolinguistics and NLP. Specifically, I’ll show that this framework can utilize recent successes in neural networks for NLP to enable scientific discovery about context- and task-dependent meaning composition in the brain, and I’ll present the first evidence that brain activity measurements of people reading can be used to improve the generalization performance of a popular deep neural network language model. These investigations also contribute advances in cognitive modeling that may be useful beyond the study of language.