@inproceedings{hsu-etal-2020-efficient,
title = "Efficient Inference For Neural Machine Translation",
author = "Hsu, Yi-Te and
Garg, Sarthak and
Liao, Yi-Hsiu and
Chatsviorkin, Ilya",
editor = "Moosavi, Nafise Sadat and
Fan, Angela and
Shwartz, Vered and
Glava{\v{s}}, Goran and
Joty, Shafiq and
Wang, Alex and
Wolf, Thomas",
booktitle = "Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.sustainlp-1.7",
doi = "10.18653/v1/2020.sustainlp-1.7",
pages = "48--53",
abstract = "Large Transformer models have achieved state-of-the-art results in neural machine translation and have become standard in the field. In this work, we look for the optimal combination of known techniques to optimize inference speed without sacrificing translation quality. We conduct an empirical study that stacks various approaches and demonstrates that combination of replacing decoder self-attention with simplified recurrent units, adopting a deep encoder and a shallow decoder architecture and multi-head attention pruning can achieve up to 109{\%} and 84{\%} speedup on CPU and GPU respectively and reduce the number of parameters by 25{\%} while maintaining the same translation quality in terms of BLEU.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hsu-etal-2020-efficient">
<titleInfo>
<title>Efficient Inference For Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi-Te</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarthak</namePart>
<namePart type="family">Garg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi-Hsiu</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilya</namePart>
<namePart type="family">Chatsviorkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nafise</namePart>
<namePart type="given">Sadat</namePart>
<namePart type="family">Moosavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Shwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Glavaš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Wolf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Transformer models have achieved state-of-the-art results in neural machine translation and have become standard in the field. In this work, we look for the optimal combination of known techniques to optimize inference speed without sacrificing translation quality. We conduct an empirical study that stacks various approaches and demonstrates that combination of replacing decoder self-attention with simplified recurrent units, adopting a deep encoder and a shallow decoder architecture and multi-head attention pruning can achieve up to 109% and 84% speedup on CPU and GPU respectively and reduce the number of parameters by 25% while maintaining the same translation quality in terms of BLEU.</abstract>
<identifier type="citekey">hsu-etal-2020-efficient</identifier>
<identifier type="doi">10.18653/v1/2020.sustainlp-1.7</identifier>
<location>
<url>https://aclanthology.org/2020.sustainlp-1.7</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>48</start>
<end>53</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Inference For Neural Machine Translation
%A Hsu, Yi-Te
%A Garg, Sarthak
%A Liao, Yi-Hsiu
%A Chatsviorkin, Ilya
%Y Moosavi, Nafise Sadat
%Y Fan, Angela
%Y Shwartz, Vered
%Y Glavaš, Goran
%Y Joty, Shafiq
%Y Wang, Alex
%Y Wolf, Thomas
%S Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F hsu-etal-2020-efficient
%X Large Transformer models have achieved state-of-the-art results in neural machine translation and have become standard in the field. In this work, we look for the optimal combination of known techniques to optimize inference speed without sacrificing translation quality. We conduct an empirical study that stacks various approaches and demonstrates that combination of replacing decoder self-attention with simplified recurrent units, adopting a deep encoder and a shallow decoder architecture and multi-head attention pruning can achieve up to 109% and 84% speedup on CPU and GPU respectively and reduce the number of parameters by 25% while maintaining the same translation quality in terms of BLEU.
%R 10.18653/v1/2020.sustainlp-1.7
%U https://aclanthology.org/2020.sustainlp-1.7
%U https://doi.org/10.18653/v1/2020.sustainlp-1.7
%P 48-53
Markdown (Informal)
[Efficient Inference For Neural Machine Translation](https://aclanthology.org/2020.sustainlp-1.7) (Hsu et al., sustainlp 2020)
ACL
- Yi-Te Hsu, Sarthak Garg, Yi-Hsiu Liao, and Ilya Chatsviorkin. 2020. Efficient Inference For Neural Machine Translation. In Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing, pages 48–53, Online. Association for Computational Linguistics.