跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 13 天前AI 評分40

成人詞語延伸與人工詞語學習中的視覺相似性

Visual Similarity in Adult Word Extension and Artificial Word Learning

AI 導讀

研究顯示,DINOv2 測得的視覺相似性部分解釋成人和人工學習者如何泛化詞語,而教學例子的組成亦提供額外影響。成人看到三個例子後,若例子屬下位類別,會把詞語延伸至 1.1% 的上位類別項目;若例子屬上位類別,比例則為 77.5%。人工學習者對近、中、遠類別配對的命名準確率分別為 84.7%、65.4% 和 53.0%。

正文

Published on Nov 10

Authors:

Abstract

Visual similarity measured by a self-supervised visual encoder partially explains word generalization in adults and artificial learners, while the composition of teaching examples contributes additional structure beyond that distance.

When two objects share a name, how much does their visual similarity explain, and what do the teaching examples add? First, we reanalyzed trial-level data from a large adult word-extension study (Lewis & Frank, 2018), computing each test image's distance to the examples shown in the space of a frozen self-supervised visual encoder (DINOv2). Distance was associated with extension (log odds -3.23 per standard deviation; 520 people), and an exploratory post hoc analysis suggested that this association persisted within the taught domain after controlling for taxonomic level and teaching condition. Example composition also mattered: after three examples, adults extended a word to 1.1% of superordinate items when the examples were subordinate and to 77.5% when they were superordinate. Second, in an artificial learner using the same encoder, words joining two categories were learned less accurately the farther apart the categories were (84.7%, 65.4%, and 53.0% naming accuracy for near, mid, and far pairs). The encoder's distances correlated with human similarity and confusability measures from three datasets (rho = .501-.795), but this representational alignment did not translate into conclusive evidence that human-derived distances predict learner difficulty, and a second encoder trained on one child's experience reproduced the tier ordering but not the pair-level effect. The secondary human data were analyzed under an internal plan fixed before the confirmatory analyses (not externally preregistered). Visual similarity accounts for part of how generalization is organized in both systems, while the composition of examples contributes what the distance we used does not capture.

View arXiv page View PDF Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.14116 in a model README.md to link it from this page.

Datasets citing this paper 2

MrPatoVera/lexical-consensus-data

Viewer •

Updated 18 minutes ago

•

5.24k

•

100

MrPatoVera/lexical-consensus-data-cifar10h

Viewer •

Updated 18 minutes ago

•

55

•

75

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.14116 in a Space README.md to link it from this page.

Collections including this paper 1

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co