@inproceedings{xin-etal-2020-early,
title = "Early Exiting {BERT} for Efficient Document Ranking",
author = "Xin, Ji and
Nogueira, Rodrigo and
Yu, Yaoliang and
Lin, Jimmy",
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-1.11",
doi = "10.18653/v1/2020.sustainlp-1.11",
pages = "83--88",
abstract = "Pre-trained language models such as BERT have shown their effectiveness in various tasks. Despite their power, they are known to be computationally intensive, which hinders real-world applications. In this paper, we introduce early exiting BERT for document ranking. With a slight modification, BERT becomes a model with multiple output paths, and each inference sample can exit early from these paths. In this way, computation can be effectively allocated among samples, and overall system latency is significantly reduced while the original quality is maintained. Our experiments on two document ranking datasets demonstrate up to 2.5x inference speedup with minimal quality degradation. The source code of our implementation can be found at \url{https://github.com/castorini/earlyexiting-monobert}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xin-etal-2020-early">
<titleInfo>
<title>Early Exiting BERT for Efficient Document Ranking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ji</namePart>
<namePart type="family">Xin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrigo</namePart>
<namePart type="family">Nogueira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaoliang</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimmy</namePart>
<namePart type="family">Lin</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>Pre-trained language models such as BERT have shown their effectiveness in various tasks. Despite their power, they are known to be computationally intensive, which hinders real-world applications. In this paper, we introduce early exiting BERT for document ranking. With a slight modification, BERT becomes a model with multiple output paths, and each inference sample can exit early from these paths. In this way, computation can be effectively allocated among samples, and overall system latency is significantly reduced while the original quality is maintained. Our experiments on two document ranking datasets demonstrate up to 2.5x inference speedup with minimal quality degradation. The source code of our implementation can be found at https://github.com/castorini/earlyexiting-monobert.</abstract>
<identifier type="citekey">xin-etal-2020-early</identifier>
<identifier type="doi">10.18653/v1/2020.sustainlp-1.11</identifier>
<location>
<url>https://aclanthology.org/2020.sustainlp-1.11</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>83</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Early Exiting BERT for Efficient Document Ranking
%A Xin, Ji
%A Nogueira, Rodrigo
%A Yu, Yaoliang
%A Lin, Jimmy
%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 xin-etal-2020-early
%X Pre-trained language models such as BERT have shown their effectiveness in various tasks. Despite their power, they are known to be computationally intensive, which hinders real-world applications. In this paper, we introduce early exiting BERT for document ranking. With a slight modification, BERT becomes a model with multiple output paths, and each inference sample can exit early from these paths. In this way, computation can be effectively allocated among samples, and overall system latency is significantly reduced while the original quality is maintained. Our experiments on two document ranking datasets demonstrate up to 2.5x inference speedup with minimal quality degradation. The source code of our implementation can be found at https://github.com/castorini/earlyexiting-monobert.
%R 10.18653/v1/2020.sustainlp-1.11
%U https://aclanthology.org/2020.sustainlp-1.11
%U https://doi.org/10.18653/v1/2020.sustainlp-1.11
%P 83-88
Markdown (Informal)
[Early Exiting BERT for Efficient Document Ranking](https://aclanthology.org/2020.sustainlp-1.11) (Xin et al., sustainlp 2020)
ACL
- Ji Xin, Rodrigo Nogueira, Yaoliang Yu, and Jimmy Lin. 2020. Early Exiting BERT for Efficient Document Ranking. In Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing, pages 83–88, Online. Association for Computational Linguistics.