论文信息 - Learning Distributed Representations by Mapping Concepts and Relations into a Linear Space

Learning Distributed Representations by Mapping Concepts and Relations into a Linear Space

Linear Relational Embedding is a method of learning a distributed representation of concepts from data consisting of binary relations between concepts. Concepts are represented as vectors, binary relations as matrices, and the operation of applying a relation to a concept as a matrix-vector multiplication that produces an approximation to the related concept. A representation for concepts and relations is learned by maximizing an appropriate discriminative goodness function using gradient ascent. On a task involving family relationships, learning is fast and leads to good generalization.

Geoffrey E. Hinton | Alberto Paccanaro | A. Paccanaro

[1] J. Kruskal. Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis , 1964 .

[2] Martin Fodslette Meiller. A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[3] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[4] Joshua B. Tenenbaum,et al. Separating Style and Content , 1996, NIPS.

[5] T. Landauer,et al. Indexing by Latent Semantic Analysis , 1990 .

[6] T. Landauer,et al. A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. , 1997 .

[7] Geoffrey E. Hinton,et al. Learning distributed representations of concepts. , 1989 .

[8] Peter W. Foltz,et al. Learning Human-like Knowledge by Singular Value Decomposition: A Progress Report , 1997, NIPS.

[9] Forrest W. Young. Multidimensional Scaling: History, Theory, and Applications , 1987 .