@inproceedings{a-rodriguez-merlo-2020-word,
title = "Word associations and the distance properties of context-aware word embeddings",
author = "A. Rodriguez, Maria and
Merlo, Paola",
editor = "Fern{\'a}ndez, Raquel and
Linzen, Tal",
booktitle = "Proceedings of the 24th Conference on Computational Natural Language Learning",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.conll-1.30",
doi = "10.18653/v1/2020.conll-1.30",
pages = "376--385",
abstract = "What do people know when they know the meaning of words? Word associations have been widely used to tap into lexical repre- sentations and their structure, as a way of probing semantic knowledge in humans. We investigate whether current word embedding spaces (contextualized and uncontextualized) can be considered good models of human lexi- cal knowledge by studying whether they have comparable characteristics to human associa- tion spaces. We study the three properties of association rank, asymmetry of similarity and triangle inequality. We find that word embeddings are good mod- els of some word associations properties. They replicate well human associations between words, and, like humans, their context-aware variants show violations of the triangle in- equality. While they do show asymmetry of similarities, their asymmetries do not map those of human association norms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="a-rodriguez-merlo-2020-word">
<titleInfo>
<title>Word associations and the distance properties of context-aware word embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">A. Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Fernández</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>What do people know when they know the meaning of words? Word associations have been widely used to tap into lexical repre- sentations and their structure, as a way of probing semantic knowledge in humans. We investigate whether current word embedding spaces (contextualized and uncontextualized) can be considered good models of human lexi- cal knowledge by studying whether they have comparable characteristics to human associa- tion spaces. We study the three properties of association rank, asymmetry of similarity and triangle inequality. We find that word embeddings are good mod- els of some word associations properties. They replicate well human associations between words, and, like humans, their context-aware variants show violations of the triangle in- equality. While they do show asymmetry of similarities, their asymmetries do not map those of human association norms.</abstract>
<identifier type="citekey">a-rodriguez-merlo-2020-word</identifier>
<identifier type="doi">10.18653/v1/2020.conll-1.30</identifier>
<location>
<url>https://aclanthology.org/2020.conll-1.30</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>376</start>
<end>385</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word associations and the distance properties of context-aware word embeddings
%A A. Rodriguez, Maria
%A Merlo, Paola
%Y Fernández, Raquel
%Y Linzen, Tal
%S Proceedings of the 24th Conference on Computational Natural Language Learning
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F a-rodriguez-merlo-2020-word
%X What do people know when they know the meaning of words? Word associations have been widely used to tap into lexical repre- sentations and their structure, as a way of probing semantic knowledge in humans. We investigate whether current word embedding spaces (contextualized and uncontextualized) can be considered good models of human lexi- cal knowledge by studying whether they have comparable characteristics to human associa- tion spaces. We study the three properties of association rank, asymmetry of similarity and triangle inequality. We find that word embeddings are good mod- els of some word associations properties. They replicate well human associations between words, and, like humans, their context-aware variants show violations of the triangle in- equality. While they do show asymmetry of similarities, their asymmetries do not map those of human association norms.
%R 10.18653/v1/2020.conll-1.30
%U https://aclanthology.org/2020.conll-1.30
%U https://doi.org/10.18653/v1/2020.conll-1.30
%P 376-385
Markdown (Informal)
[Word associations and the distance properties of context-aware word embeddings](https://aclanthology.org/2020.conll-1.30) (A. Rodriguez & Merlo, CoNLL 2020)
ACL