08/12/2020

comp-syn: Perceptually Grounded Word Embeddings with Color

Bhargav Srinivasa Desikan, Tasker Hull, Ethan Nadler, Douglas Guilbeault, Aabir Abubakar Kar, Mark Chu, Donald Ruggiero Lo Sardo

Keywords:

Abstract Paper Similar Papers

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 forover 40,000 English words, each associated with crowd-sourced word concreteness judgments.

The video of this talk cannot be embedded. You can watch it here:
https://underline.io/lecture/6291-comp-syn-perceptually-grounded-word-embeddings-with-color
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at COLING 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 14:02 
 0
 0
 0
 0
 11:49 
 0
 0
 0
 0
 12:11 
 0
 0
 0
 0
 11:59 
 0
 0
 0
 0
 14:42 
 0
 0
 0
 0
 11:20 
 0
 0
 0
 0
 13:01 
 0
 0
 0
 0
 6:02 
 0
 0
 0
 0
 12:17 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 21:47 
 0
 0
 0
 0
 11:43 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 18:06 
 0
 0
 0
 0
 17:39 
 0
 0
 0
 0
 11:24 
 0
 0
 0
 0
 15:20 
 0
 0
 0
 0
 4:00 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 0:59 
 0
 0
 0
 0
 15:58 
 0
 0
 0
 0
 8:08 
 0
 0
 0
 0
 12:07 
 0
 0
 0
 0
 10:39 
 0
 0
 0
 0
 10:34 
 0
 0
 0
 1
 10:41 
 0
 0
 0
 0
 9:40 
 0
 0
 0
 0
 11:34 
 0
 0
 0
 0
 12:23 
 0
 0
 0
 0
 10:15 
 0
 0
 0
 0
 12:25 
 0
 0
 0
 0
 5:02 
 0
 0
 0
 0
 11:47 
 0
 0
 0
 0
 6:35 
 0
 0
 0
 0
 10:53 
 0
 0
 0
 0
 14:27 
 0
 0
 0
 0
 18:56 
 0
 0
 0
 0
 12:24 
 0
 0
 0
 0
 17:52 
 0
 0
 0
 0
 2:56