InterSpeech 2011

Neural Representations of Word Meanings

Tom M. Mitchell (Carnegie Mellon University)

How does the human brain represent meanings of words and pictures in terms of neural activity? This talk will present our research addressing this question, by applying machine learning algorithms to fMRI and MEG brain image data. One line of our research involves training classifiers that identify which word a person is thinking about, based on their observed neural activity. A second line involves training computational models that predict the neural activity associated with arbitrary English words, including words for which we do not yet have brain image data. A third line of work involves examining neural activity at millisecond time resolution during the comprehension of words and phrases.