Interpretable Semantic Vectors from a Joint Model of Brain- and Text- Based Meaning
作者： Alona Fyshe , Partha P Talukdar , Brian Murphy , Tom M Mitchell , None
DOI: 10.3115/V1/P14-1046
关键词:
摘要: Vector space models (VSMs) represent word meanings as points in a high dimensional space. VSMs are typically created using large text corpora, and so semantics observed text. We present new algorithm (JNNSE) that can incorporate measure of not previously used to create VSMs: brain activation data recorded while people read words. The resulting model takes advantage the complementary strengths weaknesses corpus give more complete representation semantics. Evaluations show 1) matches behavioral closely, 2) be predict for unseen words 3) has predictive power generalizes across imaging technologies subjects. believe is thus faithful mental vocabularies.
aclweb.org参考文章(32)
Indrayana Rustandi, Marcel Just, Tom Mitchell, None, Integrating Multiple-Study Multiple-Subject fMRI Datasets Using Canonical Correlation Analysis Proceedings of the MICCAI 2009 Workshop: Statistical modeling and detection issues in intra- and inter-subject functional MRI data analysis. ,(2009) , 10.1184/R1/6475814.V1
Alona Fyshe, Brian Murphy, Partha Talukdar, Tom Mitchell, None, Documents and Dependencies: an Exploration of Vector Space Models for Semantic Composition conference on computational natural language learning. pp. 84- 93 ,(2013)
Brian Murphy, Tom Mitchell, Partha Talukdar, Learning Effective and Interpretable Semantic Models using Non-Negative Sparse Embedding international conference on computational linguistics. pp. 1933- 1950 ,(2012)
Patrick Hanks, Kenneth Ward Church, Word association norms, mutual information, and lexicography Computational Linguistics. ,vol. 16, pp. 22- 29 ,(1990) , 10.5555/89086.89095
P. D. Turney, P. Pantel, From frequency to meaning: vector space models of semantics Journal of Artificial Intelligence Research. ,vol. 37, pp. 141- 188 ,(2010) , 10.1613/JAIR.2934
Brian Murphy, Partha Talukdar, Tom Mitchell, None, Selecting Corpus-Semantic Models for Neurolinguistic Decoding joint conference on lexical and computational semantics. pp. 114- 123 ,(2012)
Andrew D. Engell, Scott Huettel, Gregory McCarthy, The fMRI BOLD signal tracks electrophysiological spectral perturbations, not event-related potentials NeuroImage. ,vol. 59, pp. 2600- 2606 ,(2012) , 10.1016/J.NEUROIMAGE.2011.08.079
Gustavo Sudre, Dean Pomerleau, Mark Palatucci, Leila Wehbe, Alona Fyshe, Riitta Salmelin, Tom Mitchell, None, Tracking neural coding of perceptual and semantic features of concrete nouns. NeuroImage. ,vol. 62, pp. 451- 463 ,(2012) , 10.1016/J.NEUROIMAGE.2012.04.048
Thomas K. Landauer, Susan T. Dumais, A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. Psychological Review. ,vol. 104, pp. 211- 240 ,(1997) , 10.1037/0033-295X.104.2.211
Bryan R. Conroy, Benjamin D. Singer, J. Swaroop Guntupalli, Peter J. Ramadge, James V. Haxby, Inter-subject alignment of human cortical anatomy using functional connectivity. NeuroImage. ,vol. 81, pp. 400- 411 ,(2013) , 10.1016/J.NEUROIMAGE.2013.05.009