Abstract
The use of neural networks for integrated linguistic analysis may be profitable. This paper presents the first results of our research on that subject: a Hopfield model for syntactical analysis. We construct a neural network as an implementation of a bounded push-down automaton, which can accept context-free languages with limited center-embedding. The network's behavior can be predicted a priori, so the presented theory can be tested. The operation of the network as an implementation of the acceptor is provably correct. Furthermore we found a solution to the problem of spurious states in Hopfield models: we use them as dynamically constructed representations of sets of states of the implemented acceptor. The so-called neural-network acceptor we propose, is fast but large.
Original language | English |
---|---|
Title of host publication | COLING-92 |
Subtitle of host publication | Proceedings of the fifteenth International Conference on Computational Linguistics |
Editors | Ch. Boitet |
Publisher | Association for Computing Machinery (ACM) |
Pages | 113-119 |
Number of pages | 7 |
DOIs | |
Publication status | Published - 23 Jul 1992 |
Event | 14th International Conference on Computational Linguistics, COLING 1992 - Nantes, France Duration: 23 Aug 1992 → 28 Aug 1992 Conference number: 14 |
Conference
Conference | 14th International Conference on Computational Linguistics, COLING 1992 |
---|---|
Abbreviated title | COLING |
Country/Territory | France |
City | Nantes |
Period | 23/08/92 → 28/08/92 |