@inproceedings{kaneko-bollegala-2020-autoencoding,
title = "Autoencoding Improves Pre-trained Word Embeddings",
author = "Kaneko, Masahiro and
Bollegala, Danushka",
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.149/",
doi = "10.18653/v1/2020.coling-main.149",
pages = "1699--1713",
abstract = "Prior works investigating the geometry of pre-trained word embeddings have shown that word embeddings to be distributed in a narrow cone and by centering and projecting using principal component vectors one can increase the accuracy of a given set of pre-trained word embeddings. However, theoretically, this post-processing step is equivalent to applying a linear autoencoder to minimize the squared L2 reconstruction error. This result contradicts prior work (Mu and Viswanath, 2018) that proposed to remove the top principal components from pre-trained embeddings. We experimentally verify our theoretical claims and show that retaining the top principal components is indeed useful for improving pre-trained word embeddings, without requiring access to additional linguistic resources or labeled data."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kaneko-bollegala-2020-autoencoding">
<titleInfo>
<title>Autoencoding Improves Pre-trained Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masahiro</namePart>
<namePart type="family">Kaneko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danushka</namePart>
<namePart type="family">Bollegala</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>Prior works investigating the geometry of pre-trained word embeddings have shown that word embeddings to be distributed in a narrow cone and by centering and projecting using principal component vectors one can increase the accuracy of a given set of pre-trained word embeddings. However, theoretically, this post-processing step is equivalent to applying a linear autoencoder to minimize the squared L2 reconstruction error. This result contradicts prior work (Mu and Viswanath, 2018) that proposed to remove the top principal components from pre-trained embeddings. We experimentally verify our theoretical claims and show that retaining the top principal components is indeed useful for improving pre-trained word embeddings, without requiring access to additional linguistic resources or labeled data.</abstract>
<identifier type="citekey">kaneko-bollegala-2020-autoencoding</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.149</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.149/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1699</start>
<end>1713</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Autoencoding Improves Pre-trained Word Embeddings
%A Kaneko, Masahiro
%A Bollegala, Danushka
%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 kaneko-bollegala-2020-autoencoding
%X Prior works investigating the geometry of pre-trained word embeddings have shown that word embeddings to be distributed in a narrow cone and by centering and projecting using principal component vectors one can increase the accuracy of a given set of pre-trained word embeddings. However, theoretically, this post-processing step is equivalent to applying a linear autoencoder to minimize the squared L2 reconstruction error. This result contradicts prior work (Mu and Viswanath, 2018) that proposed to remove the top principal components from pre-trained embeddings. We experimentally verify our theoretical claims and show that retaining the top principal components is indeed useful for improving pre-trained word embeddings, without requiring access to additional linguistic resources or labeled data.
%R 10.18653/v1/2020.coling-main.149
%U https://aclanthology.org/2020.coling-main.149/
%U https://doi.org/10.18653/v1/2020.coling-main.149
%P 1699-1713
Markdown (Informal)
[Autoencoding Improves Pre-trained Word Embeddings](https://aclanthology.org/2020.coling-main.149/) (Kaneko & Bollegala, COLING 2020)
ACL
- Masahiro Kaneko and Danushka Bollegala. 2020. Autoencoding Improves Pre-trained Word Embeddings. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1699–1713, Barcelona, Spain (Online). International Committee on Computational Linguistics.