ML Anthology

Learning Hierarchical Structures with Linear Relational Embedding

Alberto Paccanaro, Geoffrey E. Hinton
NeurIPS 2001 pp. 857-864
/neurips/2001/paccanaro2001neurips-learning/

Abstract

We present Linear Relational Embedding (LRE), a new method of learn- ing a distributed representation of concepts from data consisting of in- stances of relations between given concepts. Its final goal is to be able to generalize, i.e. infer new instances of these relations among the con- cepts. 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 representa- tions for variable-sized recursive data structures, such as trees and lists.

PDF NeurIPS Semantic Scholar

Cite

Text

Paccanaro and Hinton. "Learning Hierarchical Structures with Linear Relational Embedding." Neural Information Processing Systems, 2001.

Markdown

[Paccanaro and Hinton. "Learning Hierarchical Structures with Linear Relational Embedding." Neural Information Processing Systems, 2001.](https://mlanthology.org/neurips/2001/paccanaro2001neurips-learning/)

BibTeX

@inproceedings{paccanaro2001neurips-learning,
  title     = {{Learning Hierarchical Structures with Linear Relational Embedding}},
  author    = {Paccanaro, Alberto and Hinton, Geoffrey E.},
  booktitle = {Neural Information Processing Systems},
  year      = {2001},
  pages     = {857-864},
  url       = {https://mlanthology.org/neurips/2001/paccanaro2001neurips-learning/}
}