Article

Leveraging Context for Perceptual Prediction using Word Embeddings

2025-02-03

Abstract excerpt

<p>Word embeddings derived from large language corpora have been successfully used in cognitive science and artificial intelligence to represent linguistic meaning. However, there is continued debate as to how well they encode useful information about the perceptual qualities of concepts. This debate is critical to identifying the scope of embodiment in human semantics. If perceptual object properties can be infer...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: a13ed57e-d18e-533a-9c00-b3eabc664727
DOI: 10.31234/osf.io/34tke_v2

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Leveraging Context for Perceptual Prediction using Word EmbeddingsDOI 10.31234/osf.io/34tke_v2Read

Leveraging Context for Perceptual Prediction using Word EmbeddingsSemantic proximity Read

Conveying (discrete) emotionality with novel wordsSemantic proximity Read

Zero-shot learning of naturalistic concepts via conceptual systems alignmentSemantic proximity Read

Pathways to semantic integration: Wordform similarity and valence accelerate novel word learning from co-occurrence regularitiesSemantic proximity Read

Meaning Beyond Lexicality: Capturing Pseudoword Definitions with Language ModelsSemantic proximity Read

Flexibility in Conceptual Combinations: A Neural Network Model of Gradable Adjective ModificationSemantic proximity Read

The Primacy of Experience in Language Processing: Semantic Priming Is Driven Primarily by Experiential SimilaritySemantic proximity Read

Unified Generative Vision-Language UnderstandingSemantic proximity Read