|
|
|
|
LEADER |
01841nam a2200325Ia 4500 |
001 |
10.1111-cogs.13029 |
008 |
220427s2021 CNT 000 0 und d |
020 |
|
|
|a 03640213 (ISSN)
|
245 |
1 |
0 |
|a Distributional Models of Category Concepts Based on Names of Category Members
|
260 |
|
0 |
|b John Wiley and Sons Inc
|c 2021
|
856 |
|
|
|z View Fulltext in Publisher
|u https://doi.org/10.1111/cogs.13029
|
520 |
3 |
|
|a Cognitive scientists have long used distributional semantic representations of categories. The predominant approach uses distributional representations of category-denoting nouns, such as “city” for the category city. We propose a novel scheme that represents categories as prototypes over representations of names of its members, such as “Barcelona,” “Mumbai,” and “Wuhan” for the category city. This name-based representation empirically outperforms the noun-based representation on two experiments (modeling human judgments of category relatedness and predicting category membership) with particular improvements for ambiguous nouns. We discuss the model complexity of both classes of models and argue that the name-based model has superior explanatory potential with regard to concept acquisition. © 2021 The Authors. Cognitive Science published by Wiley Periodicals LLC on behalf of Cognitive Science Society (CSS).
|
650 |
0 |
4 |
|a Ambiguity
|
650 |
0 |
4 |
|a Concepts
|
650 |
0 |
4 |
|a Distributional semantics
|
650 |
0 |
4 |
|a human
|
650 |
0 |
4 |
|a Humans
|
650 |
0 |
4 |
|a language
|
650 |
0 |
4 |
|a Language
|
650 |
0 |
4 |
|a Names
|
650 |
0 |
4 |
|a nomenclature
|
650 |
0 |
4 |
|a Prototype theory
|
650 |
0 |
4 |
|a Relatedness
|
650 |
0 |
4 |
|a semantics
|
650 |
0 |
4 |
|a Semantics
|
700 |
1 |
|
|a Boleda, G.
|e author
|
700 |
1 |
|
|a Gupta, A.
|e author
|
700 |
1 |
|
|a Padó, S.
|e author
|
700 |
1 |
|
|a Westera, M.
|e author
|
773 |
|
|
|t Cognitive Science
|