North American Chapter of the Association for Computational Linguistics · 2010 · 10 citations · 9 references
ComputingComputer ScienceNeuroscienceCognitive NeuroscienceNeurolinguisticsSemanticsFunctional NeuroimagingNatural Language UnderstandingNeural RepresentationRepresentation LearningSemantic ProcessingText Feature EngineeringFeature-based RepresentationLexical FeaturesNeural Basis Of SemanticsNeural Feature ExtractionNeural Representation LearningSemantic Feature KnowledgeSemantic FeaturesText Feature Construction
(Mitchell et al., 2008) showed that it was possible to use a text corpus to learn the value of hypothesized semantic features characterizing the meaning of a concrete noun. The authors also demonstrated that those features could be used to decompose the spatial pattern of fMRI-measured brain activation in response to a stimulus containing that noun and a picture of it. In this paper we introduce a method for learning such semantic features automatically from a text corpus, without needing to hypothesize them or provide any proxies for their presence on the text. We show that those features are effective in a more demanding classification task than that in (Mitchell et al., 2008) and describe their qualitative relationship to the features proposed in that paper.
9
Identifying natural images from human brain activity
Kendrick Kay, Thomas Naselaris, Ryan Prenger et al. · Nature · 2008 · 1.4K citations
Predicting Human Brain Activity Associated with the Meanings of Nouns
Tom M. Mitchell, Svetlana V. Shinkareva, J. Andrew Carlson et al. · Science · 2008 · 1.2K citations · Full text