Reilly, Ronan (1992) A Connectionist technique for on-line parsing. Network: Computation in Neural Systems, 3 (1). pp. 37-45. ISSN 0954-898X

Preview

Download (235kB) | Preview

Abstract

A technique is described that permits the on-line construction and dynamic modification of parse trees during the processing of sentence-like-input. The approach is a combination of simple recurrent network (SRN) and recursive auto-associative memory (RAAM). The parsing technique involves teaching the SRN to build RAAM representations as it processes its input item by item. The approach is a potential component of a larger connectionist natural language processing system, and could also be used as a tool in the cognitive modelling of language understanding. Unfortunately, the modified SRN demonstrates a limited capacity for generalization.

Item Type:	Article
Additional Information:	This is the preprint version of the published article.
Keywords:	Connectionist technique; on-line parsing; on-line construction; dynamic modification; parse trees;
Academic Unit:	Faculty of Science and Engineering > Computer Science
Item ID:	8207
Depositing User:	Prof. Ronan Reilly
Date Deposited:	11 May 2017 15:39
Journal or Publication Title:	Network: Computation in Neural Systems
Publisher:	Taylor & Francis
Refereed:	Yes
URI:	http://www.tandfonline.com
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads