@inproceedings{shang-etal-2021-hw,
title = "{HW}-{TSC}{'}s Participation in the {WMT} 2021 Efficiency Shared Task",
author = "Shang, Hengchao and
Hu, Ting and
Wei, Daimeng and
Li, Zongyao and
Feng, Jianfei and
Yu, ZhengZhe and
Guo, Jiaxin and
Li, Shaojun and
Lei, Lizhi and
Tao, ShiMin and
Yang, Hao and
Yao, Jun and
Qin, Ying",
booktitle = "Proceedings of the Sixth Conference on Machine Translation",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wmt-1.75",
pages = "781--786",
abstract = "This paper presents the submission of Huawei Translation Services Center (HW-TSC) to WMT 2021 Efficiency Shared Task. We explore the sentence-level teacher-student distillation technique and train several small-size models that find a balance between efficiency and quality. Our models feature deep encoder, shallow decoder and light-weight RNN with SSRU layer. We use Huawei Noah{'}s Bolt, an efficient and light-weight library for on-device inference. Leveraging INT8 quantization, self-defined General Matrix Multiplication (GEMM) operator, shortlist, greedy search and caching, we submit four small-size and efficient translation models with high translation quality for the one CPU core latency track.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shang-etal-2021-hw">
<titleInfo>
<title>HW-TSC’s Participation in the WMT 2021 Efficiency Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hengchao</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daimeng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zongyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianfei</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">ZhengZhe</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaojun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizhi</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">ShiMin</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Conference on Machine Translation</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>This paper presents the submission of Huawei Translation Services Center (HW-TSC) to WMT 2021 Efficiency Shared Task. We explore the sentence-level teacher-student distillation technique and train several small-size models that find a balance between efficiency and quality. Our models feature deep encoder, shallow decoder and light-weight RNN with SSRU layer. We use Huawei Noah’s Bolt, an efficient and light-weight library for on-device inference. Leveraging INT8 quantization, self-defined General Matrix Multiplication (GEMM) operator, shortlist, greedy search and caching, we submit four small-size and efficient translation models with high translation quality for the one CPU core latency track.</abstract>
<identifier type="citekey">shang-etal-2021-hw</identifier>
<location>
<url>https://aclanthology.org/2021.wmt-1.75</url>
</location>
<part>
<date>2021-nov</date>
<extent unit="page">
<start>781</start>
<end>786</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HW-TSC’s Participation in the WMT 2021 Efficiency Shared Task
%A Shang, Hengchao
%A Hu, Ting
%A Wei, Daimeng
%A Li, Zongyao
%A Feng, Jianfei
%A Yu, ZhengZhe
%A Guo, Jiaxin
%A Li, Shaojun
%A Lei, Lizhi
%A Tao, ShiMin
%A Yang, Hao
%A Yao, Jun
%A Qin, Ying
%S Proceedings of the Sixth Conference on Machine Translation
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Online
%F shang-etal-2021-hw
%X This paper presents the submission of Huawei Translation Services Center (HW-TSC) to WMT 2021 Efficiency Shared Task. We explore the sentence-level teacher-student distillation technique and train several small-size models that find a balance between efficiency and quality. Our models feature deep encoder, shallow decoder and light-weight RNN with SSRU layer. We use Huawei Noah’s Bolt, an efficient and light-weight library for on-device inference. Leveraging INT8 quantization, self-defined General Matrix Multiplication (GEMM) operator, shortlist, greedy search and caching, we submit four small-size and efficient translation models with high translation quality for the one CPU core latency track.
%U https://aclanthology.org/2021.wmt-1.75
%P 781-786
Markdown (Informal)
[HW-TSC’s Participation in the WMT 2021 Efficiency Shared Task](https://aclanthology.org/2021.wmt-1.75) (Shang et al., WMT 2021)
ACL
- Hengchao Shang, Ting Hu, Daimeng Wei, Zongyao Li, Jianfei Feng, ZhengZhe Yu, Jiaxin Guo, Shaojun Li, Lizhi Lei, ShiMin Tao, Hao Yang, Jun Yao, and Ying Qin. 2021. HW-TSC’s Participation in the WMT 2021 Efficiency Shared Task. In Proceedings of the Sixth Conference on Machine Translation, pages 781–786, Online. Association for Computational Linguistics.