TY  - BOOK
AU  - Regier,Terry
TI  - The human semantic potential: spatial language and constrained connectionism 
T2  - Neural network modeling and connectionism
SN  - 0585032610
AV  - P37.5.S67 R44 1996eb
U1  - 401/.43 20
PY  - 1996///
KW  - Space and time in language
KW  - Semantics
KW  - Psychological aspects
KW  - Connectionism
KW  - Cognitive grammar
KW  - Linguistic models
KW  - Espace et temps dans le langage
KW  - S�emantique
KW  - Aspect psychologique
KW  - Connexionnisme
KW  - Grammaire cognitive
KW  - Mod�eles linguistiques
KW  - LANGUAGE ARTS & DISCIPLINES
KW  - Linguistics
KW  - bisacsh
KW  - fast
KW  - Cognitive semantics
KW  - gtt
KW  - Ruimtelijk inzicht
KW  - Natuurlijke taal
KW  - Connectionisme
KW  - Languages & Literatures
KW  - hilcc
KW  - Philology & Linguistics
KW  - COGNITIVE SCIENCES/General
KW  - LINGUISTICS & LANGUAGE/General
KW  - Electronic books
N1  - "A Bradford book."; Includes bibliographical references (pages 209-218) and index; 1; Introduction --; 2; The linguistic categorization of space --; 3; Connectionism and cognitive models --; 4; Learning without explicit negative evidence --; 5; Structures --; 6; A model of spatial semantics --; 7; Extensions --; 8; Discussion; Access restricted to Ryerson students, faculty and staff; Access restricted to York University faculty, staff and students; Electronic reproduction; [S.l.]; HathiTrust Digital Library; 2010
N2  - "Drawing on ideas from cognitive linguistics, connectionism, and perception, The Human Semantic Potential describes a connectionist model that learns perceptually grounded semantics for natural language in spatial terms. Languages differ in the ways in which they structure space, and Regier's aim is to have the model perform its learning task for terms from any natural language. The system has so far succeeded in learning spatial terms from English, German, Russian, Japanese, and Mixtec. The model views simple movies of two-dimensional objects moving relative to one another and learns to classify them linguistically in accordance with the spatial system of some natural language. The overall goal is to determine which sorts of spatial configurations and events are learnable as the semantics for spatial terms and which are not. Ultimately, the model and its theoretical underpinnings are a step in the direction of articulating biologically based constraints on the nature of human semantic systems. Along the way Regier takes up such substantial issues as the attraction and the liabilities of PDP and structured connectionist modeling, the problem of learning without direct negative evidence, and the area of linguistic universals, which is addressed in the model itself. Trained on spatial terms from different languages, the model permits observations about the possible bases of linguistic universals and interlanguage variation."
UR  - https://libproxy.firstcity.edu.my:8443/login?url=http://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&AN=1705
ER  -