@inproceedings{mysore-sathyendra-etal-2020-extreme,
title = "Extreme Model Compression for On-device Natural Language Understanding",
author = "Mysore Sathyendra, Kanthashree and
Choudhary, Samridhi and
Nicolich-Henkin, Leah",
editor = "Clifton, Ann and
Napoles, Courtney",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics: Industry Track",
month = dec,
year = "2020",
address = "Online",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-industry.15",
doi = "10.18653/v1/2020.coling-industry.15",
pages = "160--171",
abstract = "In this paper, we propose and experiment with techniques for extreme compression of neural natural language understanding (NLU) models, making them suitable for execution on resource-constrained devices. We propose a task-aware, end-to-end compression approach that performs word-embedding compression jointly with NLU task learning. We show our results on a large-scale, commercial NLU system trained on a varied set of intents with huge vocabulary sizes. Our approach outperforms a range of baselines and achieves a compression rate of 97.4{\%} with less than 3.7{\%} degradation in predictive performance. Our analysis indicates that the signal from the downstream task is important for effective compression with minimal degradation in performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mysore-sathyendra-etal-2020-extreme">
<titleInfo>
<title>Extreme Model Compression for On-device Natural Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kanthashree</namePart>
<namePart type="family">Mysore Sathyendra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samridhi</namePart>
<namePart type="family">Choudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leah</namePart>
<namePart type="family">Nicolich-Henkin</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: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Clifton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Courtney</namePart>
<namePart type="family">Napoles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we propose and experiment with techniques for extreme compression of neural natural language understanding (NLU) models, making them suitable for execution on resource-constrained devices. We propose a task-aware, end-to-end compression approach that performs word-embedding compression jointly with NLU task learning. We show our results on a large-scale, commercial NLU system trained on a varied set of intents with huge vocabulary sizes. Our approach outperforms a range of baselines and achieves a compression rate of 97.4% with less than 3.7% degradation in predictive performance. Our analysis indicates that the signal from the downstream task is important for effective compression with minimal degradation in performance.</abstract>
<identifier type="citekey">mysore-sathyendra-etal-2020-extreme</identifier>
<identifier type="doi">10.18653/v1/2020.coling-industry.15</identifier>
<location>
<url>https://aclanthology.org/2020.coling-industry.15</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>160</start>
<end>171</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extreme Model Compression for On-device Natural Language Understanding
%A Mysore Sathyendra, Kanthashree
%A Choudhary, Samridhi
%A Nicolich-Henkin, Leah
%Y Clifton, Ann
%Y Napoles, Courtney
%S Proceedings of the 28th International Conference on Computational Linguistics: Industry Track
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Online
%F mysore-sathyendra-etal-2020-extreme
%X In this paper, we propose and experiment with techniques for extreme compression of neural natural language understanding (NLU) models, making them suitable for execution on resource-constrained devices. We propose a task-aware, end-to-end compression approach that performs word-embedding compression jointly with NLU task learning. We show our results on a large-scale, commercial NLU system trained on a varied set of intents with huge vocabulary sizes. Our approach outperforms a range of baselines and achieves a compression rate of 97.4% with less than 3.7% degradation in predictive performance. Our analysis indicates that the signal from the downstream task is important for effective compression with minimal degradation in performance.
%R 10.18653/v1/2020.coling-industry.15
%U https://aclanthology.org/2020.coling-industry.15
%U https://doi.org/10.18653/v1/2020.coling-industry.15
%P 160-171
Markdown (Informal)
[Extreme Model Compression for On-device Natural Language Understanding](https://aclanthology.org/2020.coling-industry.15) (Mysore Sathyendra et al., COLING 2020)
ACL