A corpus-based connectionist architecture for large-scale natural language parsing

Tepper, JA ORCID logoORCID: https://orcid.org/0000-0001-7339-0132, Powell, HM and Palmer-Brown, D, 2002. A corpus-based connectionist architecture for large-scale natural language parsing. Connection Science, 14 (2), pp. 93-114. ISSN 0954-0091

Full text not available from this repository.

Abstract

We describe a deterministic shift-reduce parsing model that combines the advantages of connectionism with those of traditional symbolic models for parsing realistic sub-domains of natural language. It is a modular system that learns to annotate natural language texts with syntactic structure. The parser acquires its linguistic knowledge directly from pre-parsed sentence examples extracted from an annotated corpus. The connectionist modules enable the automatic learning of linguistic constraints and provide a distributed representation of linguistic information that exhibits tolerance to grammatical variation. The inputs and outputs of the connectionist modules represent symbolic information which can be easily manipulated and interpreted and provide the basis for organizing the parse. Performance is evaluated using labelled precision and recall. (For a test set of 4128 words, precision and recall of 75% and 69%, respectively, were achieved.) The work presented represents a significant step towards demonstrating that broad coverage parsing of natural language can be achieved with simple hybrid connectionist architectures which approximate shift-reduce parsing behaviours. Crucially, the model is adaptable to the grammatical framework of the training corpus used and so is not predisposed to a particular grammatical formalism.

Item Type: Journal article
Publication Title: Connection Science
Creators: Tepper, J.A., Powell, H.M. and Palmer-Brown, D.
Publisher: Taylor & Francis (Routledge)
Place of Publication: Abingdon
Date: 2002
Volume: 14
Number: 2
ISSN: 0954-0091
Identifiers:
Number
Type
10.1080/09540090210162074
DOI
Rights: © Informa plc
Divisions: Schools > School of Science and Technology
Record created by: EPrints Services
Date Added: 09 Oct 2015 09:51
Last Modified: 04 Feb 2022 12:38
URI: https://irep.ntu.ac.uk/id/eprint/3899

Actions (login required)

Edit View Edit View

Statistics

Views

Views per month over past year

Downloads

Downloads per month over past year