@inproceedings{srinivasa-desikan-etal-2020-comp,
title = "comp-syn: Perceptually Grounded Word Embeddings with Color",
author = "Srinivasa Desikan, Bhargav and
Hull, Tasker and
Nadler, Ethan and
Guilbeault, Douglas and
Abubakar Kar, Aabir and
Chu, Mark and
Lo Sardo, Donald Ruggiero",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.154",
doi = "10.18653/v1/2020.coling-main.154",
pages = "1744--1751",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="srinivasa-desikan-etal-2020-comp">
<titleInfo>
<title>comp-syn: Perceptually Grounded Word Embeddings with Color</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bhargav</namePart>
<namePart type="family">Srinivasa Desikan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tasker</namePart>
<namePart type="family">Hull</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ethan</namePart>
<namePart type="family">Nadler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Douglas</namePart>
<namePart type="family">Guilbeault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aabir</namePart>
<namePart type="family">Abubakar Kar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donald</namePart>
<namePart type="given">Ruggiero</namePart>
<namePart type="family">Lo Sardo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">srinivasa-desikan-etal-2020-comp</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.154</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.154</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1744</start>
<end>1751</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T comp-syn: Perceptually Grounded Word Embeddings with Color
%A Srinivasa Desikan, Bhargav
%A Hull, Tasker
%A Nadler, Ethan
%A Guilbeault, Douglas
%A Abubakar Kar, Aabir
%A Chu, Mark
%A Lo Sardo, Donald Ruggiero
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F srinivasa-desikan-etal-2020-comp
%X 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.
%R 10.18653/v1/2020.coling-main.154
%U https://aclanthology.org/2020.coling-main.154
%U https://doi.org/10.18653/v1/2020.coling-main.154
%P 1744-1751
Markdown (Informal)
[comp-syn: Perceptually Grounded Word Embeddings with Color](https://aclanthology.org/2020.coling-main.154) (Srinivasa Desikan et al., COLING 2020)
ACL
- Bhargav Srinivasa Desikan, Tasker Hull, Ethan Nadler, Douglas Guilbeault, Aabir Abubakar Kar, Mark Chu, and Donald Ruggiero Lo Sardo. 2020. comp-syn: Perceptually Grounded Word Embeddings with Color. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1744–1751, Barcelona, Spain (Online). International Committee on Computational Linguistics.