<abstract xmlns="http://www.w3.org/1999/xhtml"><p>We investigate the relationship between lexical spaces and contextually-defined conceptual spaces, offering applications to creative concept discovery. We define a computational method for discovering members of concepts based on semantic spaces: starting with a standard distributional model derived from corpus co-occurrence statistics, we dynamically select characteristic dimensions associated with seed terms, and thus a subspace of terms defining the related concept. This approach performs as well as, and in some cases better than, leading distributional semantic models on a WordNet-based concept discovery task, while also providing a model of concepts as convex regions within a space with interpretable dimensions. In particular, it performs well on more specific, contextualized concepts; to investigate this we therefore move beyond WordNet to a set of human empirical studies, in which we compare output against human responses on a membership task for novel concepts. Finally, a separate panel of judges rate both model output and human responses, showing similar ratings in many cases, and some commonalities and divergences which reveal interesting issues for computational concept discovery.</p></abstract>

We investigate the relationship between lexical spaces and contextually-defined conceptual spaces, offering applications to creative concept discovery. We define a computational method for discovering members of concepts based on semantic spaces: starting with a standard distributional model derived from corpus co-occurrence statistics, we dynamically select characteristic dimensions associated with seed terms, and thus a subspace of terms defining the related concept. This approach performs as well as, and in some cases better than, leading distributional semantic models on a WordNet-based concept discovery task, while also providing a model of concepts as convex regions within a space with interpretable dimensions. In particular, it performs well on more specific, contextualized concepts; to investigate this we therefore move beyond WordNet to a set of human empirical studies, in which we compare output against human responses on a membership task for novel concepts. Finally, a separate panel of judges rate both model output and human responses, showing similar ratings in many cases, and some commonalities and divergences which reveal interesting issues for computational concept discovery.

From Distributional Semantics to Conceptual Spaces: A Novel Computational Method for Concept Creation

School of Electronic Engineering and Computer Science, Queen Mary University of London, Mile End Road, London E1 4NS, UK

Journal of Artificial General Intelligence

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

We investigate the relationship between lexical spaces and contextually-defined conceptual spaces, offering applications to creative concept discovery. We...

From Distributional Semantics to Conceptual Spaces: A Novel Computational Method for Concept Creation

Published Online: Dec 30, 2015

Page range: 55 - 86

Received: May 24, 2015

Accepted: Nov 19, 2015

DOI: https://doi.org/10.1515/jagi-2015-0004

Keywords
distributional semantics, conceptual spaces, computational creativity, concept discovery, behavioural validation

© 2015 Stephen McGregor et al., published by De Gruyter Open

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

From Distributional Semantics to Conceptual Spaces: A Novel Computational Method for Concept Creation

Published Online: Dec 30, 2015

Page range: 55 - 86

Received: May 24, 2015

Accepted: Nov 19, 2015

DOI: https://doi.org/10.1515/jagi-2015-0004

Keywordsdistributional semantics, conceptual spaces, computational creativity, concept discovery, behavioural validation

© 2015 Stephen McGregor et al., published by De Gruyter Open

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Keywords
distributional semantics, conceptual spaces, computational creativity, concept discovery, behavioural validation