Generating Realistic Semantic Codes for Use in Neural Network Models

Ya Ning Chang, Steve Furber, Stephen Welbourne

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Many psychologically interesting tasks (e.g., reading, lexical decision, semantic categorisation and synonym judgement) require the manipulation of semantic representations. To produce a good computational model of these tasks, it is important to represent semantic information in a realistic manner. This paper aimed to find a method for generating artificial semantic codes, which would be suitable for modelling semantic knowledge. The desired computational criteria for semantic representations included: (1) binary coding; (2) sparse coding; (3) fixed number of active units in a semantic vector; (4) scalable semantic vectors and (5) preservation of realistic internal semantic structure. Several existing methods for generating semantic representations were evaluated against the criteria. The correlated occurrence analogue to the lexical semantics (COALS) system (Rohde, Gonnerman & Plaut, 2006) was selected as the most suitable candidate because it satisfied most of the desired criteria. Semantic vectors generated from the COALS system were converted into binary representations and assessed on their ability to reproduce human semantic category judgements using stimuli from a previous study (Garrard, Lambon Ralph, Hodges & Patterson, 2001). Intriguingly the best performing sets of semantic vectors included 5 positive features and 15 negative features. Positive features are elements that encode the likely presence of a particular attribute whereas negative features encode its absence. These results suggest that including both positive and negative attributes generates a better category structure than the more traditional method of selecting only positive attributes.

Original languageEnglish
Title of host publicationBuilding Bridges Across Cognitive Sciences Around the World - Proceedings of the 34th Annual Meeting of the Cognitive Science Society, CogSci 2012
EditorsNaomi Miyake, David Peebles, Richard P. Cooper
PublisherThe Cognitive Science Society
Pages198-203
Number of pages6
ISBN (Electronic)9780976831884
Publication statusPublished - 2012
Event34th Annual Meeting of the Cognitive Science Society: Building Bridges Across Cognitive Sciences Around the World, CogSci 2012 - Sapporo, Japan
Duration: 2012 Aug 12012 Aug 4

Publication series

NameBuilding Bridges Across Cognitive Sciences Around the World - Proceedings of the 34th Annual Meeting of the Cognitive Science Society, CogSci 2012

Conference

Conference34th Annual Meeting of the Cognitive Science Society: Building Bridges Across Cognitive Sciences Around the World, CogSci 2012
Country/TerritoryJapan
CitySapporo
Period12-08-0112-08-04

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Science Applications
  • Human-Computer Interaction
  • Cognitive Neuroscience

Fingerprint

Dive into the research topics of 'Generating Realistic Semantic Codes for Use in Neural Network Models'. Together they form a unique fingerprint.

Cite this