Parallel Models of Associative Memory
Parallel Models of Associative Memory
Unbounded dependency: tying strings to rings
COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 3
Distributed memory: a basis for chart parsing
COLING '86 Proceedings of the 11th coference on Computational linguistics
| Hi-index | 0.00 |
The paper begins by defining a class of distributed memory machines which have useful properties as retrieval and filtering devices. These memory mechanisms store large numbers of associations on a single composite vector. They provide a natural format for encoding the syntactic and semantic constraints associated with linguistic elements. A computational architecture for parsing natural language is proposed which utilises the retrieval and associative features of these devices. The parsing mechanism is based on the principles of Lexical Functional Grammar and the paper demonstrates how these principles can be derived from the properties of the memory mechanisms.