@inproceedings{thaine-penn-2021-chinese,
title = "The {C}hinese Remainder Theorem for Compact, Task-Precise, Efficient and Secure Word Embeddings",
author = "Thaine, Patricia and
Penn, Gerald",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.306",
doi = "10.18653/v1/2021.eacl-main.306",
pages = "3512--3521",
abstract = "The growing availability of powerful mobile devices and other edge devices, together with increasing regulatory and security concerns about the exchange of personal information across networks of these devices has challenged the Computational Linguistics community to develop methods that are at once fast, space-efficient, accurate and amenable to secure encoding schemes such as homomorphic encryption. Inspired by recent work that restricts floating point precision to speed up neural network training in hardware-based SIMD, we have developed a method for compressing word vector embeddings into integers using the Chinese Reminder Theorem that speeds up addition by up to 48.27{\%} and at the same time compresses GloVe word embedding libraries by up to 25.86{\%}. We explore the practicality of this simple approach by investigating the trade-off between precision and performance in two NLP tasks: compositional semantic relatedness and opinion target sentiment classification. We find that in both tasks, lowering floating point number precision results in negligible changes to performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thaine-penn-2021-chinese">
<titleInfo>
<title>The Chinese Remainder Theorem for Compact, Task-Precise, Efficient and Secure Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Patricia</namePart>
<namePart type="family">Thaine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerald</namePart>
<namePart type="family">Penn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-apr</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The growing availability of powerful mobile devices and other edge devices, together with increasing regulatory and security concerns about the exchange of personal information across networks of these devices has challenged the Computational Linguistics community to develop methods that are at once fast, space-efficient, accurate and amenable to secure encoding schemes such as homomorphic encryption. Inspired by recent work that restricts floating point precision to speed up neural network training in hardware-based SIMD, we have developed a method for compressing word vector embeddings into integers using the Chinese Reminder Theorem that speeds up addition by up to 48.27% and at the same time compresses GloVe word embedding libraries by up to 25.86%. We explore the practicality of this simple approach by investigating the trade-off between precision and performance in two NLP tasks: compositional semantic relatedness and opinion target sentiment classification. We find that in both tasks, lowering floating point number precision results in negligible changes to performance.</abstract>
<identifier type="citekey">thaine-penn-2021-chinese</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.306</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.306</url>
</location>
<part>
<date>2021-apr</date>
<extent unit="page">
<start>3512</start>
<end>3521</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Chinese Remainder Theorem for Compact, Task-Precise, Efficient and Secure Word Embeddings
%A Thaine, Patricia
%A Penn, Gerald
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 apr
%I Association for Computational Linguistics
%C Online
%F thaine-penn-2021-chinese
%X The growing availability of powerful mobile devices and other edge devices, together with increasing regulatory and security concerns about the exchange of personal information across networks of these devices has challenged the Computational Linguistics community to develop methods that are at once fast, space-efficient, accurate and amenable to secure encoding schemes such as homomorphic encryption. Inspired by recent work that restricts floating point precision to speed up neural network training in hardware-based SIMD, we have developed a method for compressing word vector embeddings into integers using the Chinese Reminder Theorem that speeds up addition by up to 48.27% and at the same time compresses GloVe word embedding libraries by up to 25.86%. We explore the practicality of this simple approach by investigating the trade-off between precision and performance in two NLP tasks: compositional semantic relatedness and opinion target sentiment classification. We find that in both tasks, lowering floating point number precision results in negligible changes to performance.
%R 10.18653/v1/2021.eacl-main.306
%U https://aclanthology.org/2021.eacl-main.306
%U https://doi.org/10.18653/v1/2021.eacl-main.306
%P 3512-3521
Markdown (Informal)
[The Chinese Remainder Theorem for Compact, Task-Precise, Efficient and Secure Word Embeddings](https://aclanthology.org/2021.eacl-main.306) (Thaine & Penn, EACL 2021)
ACL