Cognitive Science 34 (8):1388-1429 (2010)
AbstractVector-based models of word meaning have become increasingly popular in cognitive science. The appeal of these models lies in their ability to represent meaning simply by using distributional information under the assumption that words occurring within similar contexts are semantically similar. Despite their widespread use, vector-based models are typically directed at representing words in isolation, and methods for constructing representations for phrases or sentences have received little attention in the literature. This is in marked contrast to experimental evidence (e.g., in sentential priming) suggesting that semantic similarity is more complex than simply a relation between isolated words. This article proposes a framework for representing the meaning of word combinations in vector space. Central to our approach is vector composition, which we operationalize in terms of additive and multiplicative functions. Under this framework, we introduce a wide range of composition models that we evaluate empirically on a phrase similarity task
Added to PP
Historical graph of downloads
References found in this work
Philosophical Investigations.Ludwig Josef Johann Wittgenstein - 1953 - New York, NY, USA: Wiley-Blackwell.
The Language Instinct: How the Mind Creates Language.Steven Pinker - 1994/2007 - Harper Perennial.
Connectionism and Cognitive Architecture: A Critical Analysis.Jerry A. Fodor & Zenon W. Pylyshyn - 1988 - Cognition 28 (1-2):3-71.
Grundlagen der Arithmetik: Studienausgabe MIT Dem Text der Centenarausgabe.Gottlob Frege - 1884 - Breslau: Wilhelm Koebner Verlag.
Citations of this work
A Description Logic Framework for Commonsense Conceptual Combination Integrating Typicality, Probabilities and Cognitive Heuristics.Antonio Lieto & Gian Luca Pozzato - 2019 - Journal of Experimental and Theoretical Artificial Intelligence:1-39.
Beyond Subgoaling: A Dynamic Knowledge Generation Framework for Creative Problem Solving in Cognitive Architectures.Antonio Lieto - 2019 - Cognitive Systems Research 58:305-316.
A Probabilistic Framework for Analysing the Compositionality of Conceptual Combinations.Peter Bruza, Kirsty Kitto, Brentyn Ramm & Laurianne Sitbon - 2015 - Journal of Mathematical Psychology 67:26-38.
Perceptual Inference Through Global Lexical Similarity.Brendan T. Johns & Michael N. Jones - 2012 - Topics in Cognitive Science 4 (1):103-120.
Hierarchical Conceptual Spaces for Concept Combination.Martha Lewis & Jonathan Lawry - 2016 - Artificial Intelligence 237:204-227.
Similar books and articles
Semantic Vector Models and Functional Models for Pregroup Grammars.Anne Preller & Mehrnoosh Sadrzadeh - 2011 - Journal of Logic, Language and Information 20 (4):419-443.
An Axiomatic Characterization of Causal Counterfactuals.David Galles & Judea Pearl - 1998 - Foundations of Science 3 (1):151-182.
Chunks, Bindings, STAR, and Holographic Reduced Representations.Tony A. Plate - 1998 - Behavioral and Brain Sciences 21 (6):844-845.
Comparing Methods for Single Paragraph Similarity Analysis.Benjamin Stone, Simon Dennis & Peter J. Kwantes - 2011 - Topics in Cognitive Science 3 (1):92-122.
Semantic Priming: Perspectives From Memory and Word Recognition.Timothy P. McNamara - 2005 - Psychology Press.
Syntactic Transformations on Distributed Representations.David J. Chalmers - 1990 - Connection Science 2:53-62.
A Multiagent Approach to Modelling Complex Phenomena.Francesco Amigoni & Viola Schiaffonati - 2008 - Foundations of Science 13 (2):113-125.
Using Models to Represent Reality.Ronald N. Giere - 1999 - In L. Magnani, N. J. Nersessian & P. Thagard (eds.), Model-Based Reasoning in Scientific Discovery. Kluwer/Plenum. pp. 41--57.
Redundancy in Perceptual and Linguistic Experience: Comparing Feature-Based and Distributional Models of Semantic Representation.Brian Riordan & Michael N. Jones - 2011 - Topics in Cognitive Science 3 (2):303-345.