@inproceedings{nguyen-etal-2020-fast,
title = "Fast Word Predictor for On-Device Application",
author = "Nguyen, Huy Tien and
Nguyen, Khoi Tuan and
Nguyen, Anh Tuan and
Tran, Thanh Lac Thi",
editor = "Ptaszynski, Michal and
Ziolko, Bartosz",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics: System Demonstrations",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics (ICCL)",
url = "https://aclanthology.org/2020.coling-demos.5/",
doi = "10.18653/v1/2020.coling-demos.5",
pages = "23--27",
abstract = "Learning on large text corpora, deep neural networks achieve promising results in the next word prediction task. However, deploying these huge models on devices has to deal with constraints of low latency and a small binary size. To address these challenges, we propose a fast word predictor performing efficiently on mobile devices. Compared with a standard neural network which has a similar word prediction rate, the proposed model obtains 60{\%} reduction in memory size and 100X faster inference time on a middle-end mobile device. The method is developed as a feature for a chat application which serves more than 100 million users."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2020-fast">
<titleInfo>
<title>Fast Word Predictor for On-Device Application</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huy</namePart>
<namePart type="given">Tien</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khoi</namePart>
<namePart type="given">Tuan</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anh</namePart>
<namePart type="given">Tuan</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thanh</namePart>
<namePart type="given">Lac</namePart>
<namePart type="given">Thi</namePart>
<namePart type="family">Tran</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: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Ptaszynski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bartosz</namePart>
<namePart type="family">Ziolko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics (ICCL)</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Learning on large text corpora, deep neural networks achieve promising results in the next word prediction task. However, deploying these huge models on devices has to deal with constraints of low latency and a small binary size. To address these challenges, we propose a fast word predictor performing efficiently on mobile devices. Compared with a standard neural network which has a similar word prediction rate, the proposed model obtains 60% reduction in memory size and 100X faster inference time on a middle-end mobile device. The method is developed as a feature for a chat application which serves more than 100 million users.</abstract>
<identifier type="citekey">nguyen-etal-2020-fast</identifier>
<identifier type="doi">10.18653/v1/2020.coling-demos.5</identifier>
<location>
<url>https://aclanthology.org/2020.coling-demos.5/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>23</start>
<end>27</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fast Word Predictor for On-Device Application
%A Nguyen, Huy Tien
%A Nguyen, Khoi Tuan
%A Nguyen, Anh Tuan
%A Tran, Thanh Lac Thi
%Y Ptaszynski, Michal
%Y Ziolko, Bartosz
%S Proceedings of the 28th International Conference on Computational Linguistics: System Demonstrations
%D 2020
%8 December
%I International Committee on Computational Linguistics (ICCL)
%C Barcelona, Spain (Online)
%F nguyen-etal-2020-fast
%X Learning on large text corpora, deep neural networks achieve promising results in the next word prediction task. However, deploying these huge models on devices has to deal with constraints of low latency and a small binary size. To address these challenges, we propose a fast word predictor performing efficiently on mobile devices. Compared with a standard neural network which has a similar word prediction rate, the proposed model obtains 60% reduction in memory size and 100X faster inference time on a middle-end mobile device. The method is developed as a feature for a chat application which serves more than 100 million users.
%R 10.18653/v1/2020.coling-demos.5
%U https://aclanthology.org/2020.coling-demos.5/
%U https://doi.org/10.18653/v1/2020.coling-demos.5
%P 23-27
Markdown (Informal)
[Fast Word Predictor for On-Device Application](https://aclanthology.org/2020.coling-demos.5/) (Nguyen et al., COLING 2020)
ACL
- Huy Tien Nguyen, Khoi Tuan Nguyen, Anh Tuan Nguyen, and Thanh Lac Thi Tran. 2020. Fast Word Predictor for On-Device Application. In Proceedings of the 28th International Conference on Computational Linguistics: System Demonstrations, pages 23–27, Barcelona, Spain (Online). International Committee on Computational Linguistics (ICCL).