Tags

Type your tag names separated by a space and hit enter

Integrating experiential and distributional data to learn semantic representations.
Psychol Rev 2009; 116(3):463-98PR

Abstract

The authors identify 2 major types of statistical data from which semantic representations can be learned. These are denoted as experiential data and distributional data. Experiential data are derived by way of experience with the physical world and comprise the sensory-motor data obtained through sense receptors. Distributional data, by contrast, describe the statistical distribution of words across spoken and written language. The authors claim that experiential and distributional data represent distinct data types and that each is a nontrivial source of semantic information. Their theoretical proposal is that human semantic representations are derived from an optimal statistical combination of these 2 data types. Using a Bayesian probabilistic model, they demonstrate how word meanings can be learned by treating experiential and distributional data as a single joint distribution and learning the statistical structure that underlies it. The semantic representations that are learned in this manner are measurably more realistic-as verified by comparison to a set of human-based measures of semantic representation-than those available from either data type individually or from both sources independently. This is not a result of merely using quantitatively more data, but rather it is because experiential and distributional data are qualitatively distinct, yet intercorrelated, types of data. The semantic representations that are learned are based on statistical structures that exist both within and between the experiential and distributional data types.

Authors+Show Affiliations

Cognitive, Perceptual and Brain Sciences, University College London, London, UK. m.andrews@ucl.ac.ukNo affiliation info availableNo affiliation info available

Pub Type(s)

Journal Article
Research Support, Non-U.S. Gov't

Language

eng

PubMed ID

19618982

Citation

Andrews, Mark, et al. "Integrating Experiential and Distributional Data to Learn Semantic Representations." Psychological Review, vol. 116, no. 3, 2009, pp. 463-98.
Andrews M, Vigliocco G, Vinson D. Integrating experiential and distributional data to learn semantic representations. Psychol Rev. 2009;116(3):463-98.
Andrews, M., Vigliocco, G., & Vinson, D. (2009). Integrating experiential and distributional data to learn semantic representations. Psychological Review, 116(3), pp. 463-98. doi:10.1037/a0016261.
Andrews M, Vigliocco G, Vinson D. Integrating Experiential and Distributional Data to Learn Semantic Representations. Psychol Rev. 2009;116(3):463-98. PubMed PMID: 19618982.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Integrating experiential and distributional data to learn semantic representations. AU - Andrews,Mark, AU - Vigliocco,Gabriella, AU - Vinson,David, PY - 2009/7/22/entrez PY - 2009/7/22/pubmed PY - 2009/9/29/medline SP - 463 EP - 98 JF - Psychological review JO - Psychol Rev VL - 116 IS - 3 N2 - The authors identify 2 major types of statistical data from which semantic representations can be learned. These are denoted as experiential data and distributional data. Experiential data are derived by way of experience with the physical world and comprise the sensory-motor data obtained through sense receptors. Distributional data, by contrast, describe the statistical distribution of words across spoken and written language. The authors claim that experiential and distributional data represent distinct data types and that each is a nontrivial source of semantic information. Their theoretical proposal is that human semantic representations are derived from an optimal statistical combination of these 2 data types. Using a Bayesian probabilistic model, they demonstrate how word meanings can be learned by treating experiential and distributional data as a single joint distribution and learning the statistical structure that underlies it. The semantic representations that are learned in this manner are measurably more realistic-as verified by comparison to a set of human-based measures of semantic representation-than those available from either data type individually or from both sources independently. This is not a result of merely using quantitatively more data, but rather it is because experiential and distributional data are qualitatively distinct, yet intercorrelated, types of data. The semantic representations that are learned are based on statistical structures that exist both within and between the experiential and distributional data types. SN - 0033-295X UR - https://www.unboundmedicine.com/medline/citation/19618982/Integrating_experiential_and_distributional_data_to_learn_semantic_representations_ L2 - http://content.apa.org/journals/rev/116/3/463 DB - PRIME DP - Unbound Medicine ER -