comp-syn: Perceptually Grounded Word Embeddings with Color
Abstract
Popular approaches to natural language processing create word embeddings based on textual co-occurrence patterns, but often ignore embodied, sensory aspects of language. Here, we introduce the Python package comp-syn, which provides grounded word embeddings based on the perceptually uniform color distributions of Google Image search results. We demonstrate that comp-syn significantly enriches models of distributional semantics. In particular, we show that (1) comp-syn predicts human judgments of word concreteness with greater accuracy and in a more interpretable fashion than word2vec using low-dimensional word-color embeddings, and (2) comp-syn performs comparably to word2vec on a metaphorical vs. literal word-pair classification task. comp-syn is open-source on PyPi and is compatible with mainstream machine-learning Python packages. Our package release includes word-color embeddings for over 40,000 English words, each associated with crowd-sourced word concreteness judgments.
Cite
@article{arxiv.2010.04292,
title = {comp-syn: Perceptually Grounded Word Embeddings with Color},
author = {Bhargav Srinivasa Desikan and Tasker Hull and Ethan O. Nadler and Douglas Guilbeault and Aabir Abubaker Kar and Mark Chu and Donald Ruggiero Lo Sardo},
journal= {arXiv preprint arXiv:2010.04292},
year = {2020}
}
Comments
9 pages, 3 figures, all code and data available at https://github.com/comp-syn/comp-syn. Forthcoming in the Proceedings of the 28th International Conference on Computational Linguistics