Words whose caption-embedding neighborhoods are stable under nearest-neighbor agreement are rated by humans as more imageable and concrete, and this stability score outperforms prior unsupervised predictors.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Uncovering Visual-Semantic Psycholinguistic Properties from the Distributional Structure of Text Embedding Space
Words whose caption-embedding neighborhoods are stable under nearest-neighbor agreement are rated by humans as more imageable and concrete, and this stability score outperforms prior unsupervised predictors.