Search research articles

Search research articles

Related Experiment Videos

Connectionist natural language parsing.

Dominic Palmer-Brown¹, Jonathan A. Tepper, Heather M. Powell

¹Leeds Metropolitan University, Computational Intelligence Research Group, School of Computing, Beckett Park, LS6 3QS, Leeds, UK

Trends in Cognitive Sciences

|November 5, 2002

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Snap-drift neural network for self-organisation and sequence learning.

Neural networks : the official journal of the International Neural Network Society·2011

Same author

2002 Rumelhart prizewinner.

Trends in cognitive sciences·2001

Same journal

Misinformation as strategy: Epistemic consequences and the undermining of shared truth.

Trends in cognitive sciences·2026

Same journal

Geographical psychology: Spatial variation in psychological phenomena and their consequences.

Trends in cognitive sciences·2026

Same journal

Multi-brain neurofeedback: what are we training for?

Trends in cognitive sciences·2026

Same journal

The developing vocal self.

Trends in cognitive sciences·2026

Same journal

Searching beyond decrements: Attentional guidance across the adult lifespan.

Trends in cognitive sciences·2026

Same journal

Looking into working memory through micro eye movements.

Trends in cognitive sciences·2026

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

This review examines connectionist parsing, focusing on automatic syntactic structure learning and its role as a computational model for human sentence processing and psycholinguistic data. It assesses parsers

Area of Science:

Computational Linguistics
Cognitive Science
Artificial Intelligence

Background:

Connectionist parsing models aim to learn syntactic structures automatically from data, bypassing explicit symbolic grammar rules.
Two decades of research have advanced these models, exploring their potential in natural language processing.

Purpose of the Study:

To review key developments in connectionist parsing over the past twenty years.
To assess connectionist parsers' ability for automatic syntactic structure representation.
To evaluate connectionist parsers as computational models of human sentence processing and psycholinguistic data.

Main Methods:

Systematic review of connectionist parsing literature.
Assessment of parsers based on learning capabilities, computational modeling, and psycholinguistic plausibility.

Related Experiment Videos

Analysis of realism, modularity, and processing types across various connectionist parsers.

Main Results:

Connectionist parsers demonstrate varying degrees of success in learning syntactic structures without explicit rules.
The models offer insights into human sentence processing, with some providing plausible accounts of psycholinguistic findings.
Key considerations include the level of realism, modularity, and processing mechanisms employed.

Conclusions:

Connectionist parsing has evolved significantly, offering valuable computational models for language acquisition and processing.
Further research is needed to enhance realism and align models more closely with human cognitive processes.