Semantic oscillations : encoding context and structure in complex valued holographic vectors
Data(s) |
01/12/2010
|
---|---|
Resumo |
In computational linguistics, information retrieval and applied cognition, words and concepts are often represented as vectors in high dimensional spaces computed from a corpus of text. These high dimensional spaces are often referred to as Semantic Spaces. We describe a novel and efficient approach to computing these semantic spaces via the use of complex valued vector representations. We report on the practical implementation of the proposed method and some associated experiments. We also briefly discuss how the proposed system relates to previous theoretical work in Information Retrieval and Quantum Mechanics and how the notions of probability, logic and geometry are integrated within a single Hilbert space representation. In this sense the proposed system has more general application and gives rise to a variety of opportunities for future research. |
Formato |
application/pdf |
Identificador | |
Publicador |
AAAI Press |
Relação |
http://eprints.qut.edu.au/39337/1/c39337.pdf http://www.aaai.org/ocs/index.php/FSS/FSS10/paper/view/2277 De Vine, Lance & Bruza, Peter D. (2010) Semantic oscillations : encoding context and structure in complex valued holographic vectors. In Quantum Informatics for Cognitive, Social, and Semantic Processes (QI 2010), AAAI Press, Arlington, Virginia. http://purl.org/au-research/grants/ARC/DP1094974 |
Direitos |
Copyright 2010 American Association for Artificial Intelligence (www.aaai.org). All rights reserved. |
Fonte |
Faculty of Science and Technology; High Performance Computing and Research Support; Information Systems |
Palavras-Chave | #020603 Quantum Information Computation and Communication #080107 Natural Language Processing #080603 Conceptual Modelling #quantum #language #semantics #representation |
Tipo |
Conference Paper |