Are Distributional Representations Ready for the Real World? Evaluating Word Vectors for Grounded Perceptual Meaning
Year: 2017
Type: conference-paper
Abstract: Distributionalword representation methods exploit word co-occurrences to build compact vector encodings of words.While these representations enjoy widespread use in modern natural language processing, it is unclear whether they accurately encode all necessary facets of conceptual meaning.In this paper, we evaluate how well these representations can predict perceptual and conceptual features of concrete concepts, drawing on two semantic norm datasets sourced from human participants.We find that several standard word representations fail to encode many salient perceptual features of concepts, and show that these deficits correlate with word-word similarity prediction errors.Our analyses provide motivation for grounded and embodied language learning approaches, which may help to remedy these deficits.
DOI: 10.18653/v1/w17-2810
Authors: Li Lucy, Jon Gauthier
Institution: Stanford University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Funder: University of Washington
OpenAlex ID: W2963583512
