论文信息 - Learning Hierarchical Structures with Linear Relational Embedding

Learning Hierarchical Structures with Linear Relational Embedding

We present Linear Relational Embedding (LRE), a new method of learning a distributed representation of concepts from data consisting of instances of relations between given concepts. Its final goal is to be able to generalize, i.e. infer new instances of these relations among the concepts. On a task involving family relationships we show that LRE can generalize better than any previously published method. We then show how LRE can be used effectively to find compact distributed representations for variable-sized recursive data structures, such as trees and lists.

Geoffrey E. Hinton | Alberto Paccanaro | A. Paccanaro

[1] James L. McClelland,et al. Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[2] Geoffrey E. Hinton. Learning distributed representations of concepts. , 1989 .

[3] Jordan B. Pollack,et al. Recursive Distributed Representations , 1990, Artif. Intell..

[4] J. R. Quinlan. Learning Logical Definitions from Relations , 1990 .

[5] Geoffrey E. Hinton,et al. Distributed Representations , 1986, The Philosophy of Artificial Intelligence.

[6] Geoffrey E. Hinton,et al. Learning Distributed Representations of Relational Data using Linear Relational Embedding , 2001, WIRN.

[7] Geoffrey E. Hinton,et al. Learning Distributed Representations by Mapping Concepts and Relations into a Linear Space , 2000, ICML.