TY - GEN
T1 - Generating Realistic Semantic Codes for Use in Neural Network Models
AU - Chang, Ya Ning
AU - Furber, Steve
AU - Welbourne, Stephen
N1 - Funding Information:
This research was supported by grants under the Cognitive Foresight Initiative (jointly funded by EPSRC, MRC and BBSRC - EP/F03430X/1) and the Neuroscience Research Institute at the University of Manchester.
Publisher Copyright:
© CogSci 2012.All rights reserved.
PY - 2012
Y1 - 2012
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85065962078&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85065962078&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85065962078
T3 - Building Bridges Across Cognitive Sciences Around the World - Proceedings of the 34th Annual Meeting of the Cognitive Science Society, CogSci 2012
SP - 198
EP - 203
BT - Building Bridges Across Cognitive Sciences Around the World - Proceedings of the 34th Annual Meeting of the Cognitive Science Society, CogSci 2012
A2 - Miyake, Naomi
A2 - Peebles, David
A2 - Cooper, Richard P.
PB - The Cognitive Science Society
T2 - 34th Annual Meeting of the Cognitive Science Society: Building Bridges Across Cognitive Sciences Around the World, CogSci 2012
Y2 - 1 August 2012 through 4 August 2012
ER -