@inproceedings{yang-etal-2020-textbrewer,
title = "{T}ext{B}rewer: {A}n {O}pen-{S}ource {K}nowledge {D}istillation {T}oolkit for {N}atural {L}anguage {P}rocessing",
author = "Yang, Ziqing and
Cui, Yiming and
Chen, Zhipeng and
Che, Wanxiang and
Liu, Ting and
Wang, Shijin and
Hu, Guoping",
editor = "Celikyilmaz, Asli and
Wen, Tsung-Hsien",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-demos.2/",
doi = "10.18653/v1/2020.acl-demos.2",
pages = "9--16",
abstract = "In this paper, we introduce TextBrewer, an open-source knowledge distillation toolkit designed for natural language processing. It works with different neural network models and supports various kinds of supervised learning tasks, such as text classification, reading comprehension, sequence labeling. TextBrewer provides a simple and uniform workflow that enables quick setting up of distillation experiments with highly flexible configurations. It offers a set of predefined distillation methods and can be extended with custom code. As a case study, we use TextBrewer to distill BERT on several typical NLP tasks. With simple configurations, we achieve results that are comparable with or even higher than the public distilled BERT models with similar numbers of parameters."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2020-textbrewer">
<titleInfo>
<title>TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ziqing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhipeng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shijin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoping</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsung-Hsien</namePart>
<namePart type="family">Wen</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>In this paper, we introduce TextBrewer, an open-source knowledge distillation toolkit designed for natural language processing. It works with different neural network models and supports various kinds of supervised learning tasks, such as text classification, reading comprehension, sequence labeling. TextBrewer provides a simple and uniform workflow that enables quick setting up of distillation experiments with highly flexible configurations. It offers a set of predefined distillation methods and can be extended with custom code. As a case study, we use TextBrewer to distill BERT on several typical NLP tasks. With simple configurations, we achieve results that are comparable with or even higher than the public distilled BERT models with similar numbers of parameters.</abstract>
<identifier type="citekey">yang-etal-2020-textbrewer</identifier>
<identifier type="doi">10.18653/v1/2020.acl-demos.2</identifier>
<location>
<url>https://aclanthology.org/2020.acl-demos.2/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>9</start>
<end>16</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing
%A Yang, Ziqing
%A Cui, Yiming
%A Chen, Zhipeng
%A Che, Wanxiang
%A Liu, Ting
%A Wang, Shijin
%A Hu, Guoping
%Y Celikyilmaz, Asli
%Y Wen, Tsung-Hsien
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F yang-etal-2020-textbrewer
%X In this paper, we introduce TextBrewer, an open-source knowledge distillation toolkit designed for natural language processing. It works with different neural network models and supports various kinds of supervised learning tasks, such as text classification, reading comprehension, sequence labeling. TextBrewer provides a simple and uniform workflow that enables quick setting up of distillation experiments with highly flexible configurations. It offers a set of predefined distillation methods and can be extended with custom code. As a case study, we use TextBrewer to distill BERT on several typical NLP tasks. With simple configurations, we achieve results that are comparable with or even higher than the public distilled BERT models with similar numbers of parameters.
%R 10.18653/v1/2020.acl-demos.2
%U https://aclanthology.org/2020.acl-demos.2/
%U https://doi.org/10.18653/v1/2020.acl-demos.2
%P 9-16
Markdown (Informal)
[TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing](https://aclanthology.org/2020.acl-demos.2/) (Yang et al., ACL 2020)
ACL