TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing

被引:0
|
作者
Yang, Ziqing [1 ]
Cui, Yiming [1 ,2 ]
Chen, Zhipeng [1 ]
Che, Wanxiang [2 ]
Liu, Ting [2 ]
Wang, Shijin [1 ,3 ]
Hu, Guoping [1 ]
机构
[1] iFLYTEK Res, State Key Lab Cognit Intelligence, Hefei, Anhui, Peoples R China
[2] Harbin Inst Technol, Res Ctr Social Comp & Informat Retrieval SCIR, Harbin, Peoples R China
[3] iFLYTEK AI Res Hebei, Langfang, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.(1)
引用
收藏
页码:9 / 16
页数:8
相关论文
共 50 条
  • [1] nutIE - A modern open source natural language processing toolkit
    Zitnik, Slavko
    Draskovic, Drazen
    Nikolic, Bosko
    Bajec, Marko
    [J]. 2017 25TH TELECOMMUNICATION FORUM (TELFOR), 2017, : 880 - 883
  • [2] A set of open-source tools for Turkish natural language processing
    Coltekin, Cagri
    [J]. LREC 2014 - NINTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2014, : 1079 - 1086
  • [3] Pyradi: an open-source toolkit for infrared calculation and data processing
    Willers, Cornelius J.
    Willers, Maria S.
    Santos, Ricardo Augusto T.
    van der Merwe, Petrus J.
    Calitz, Johannes J.
    de Waal, Alta
    Mudau, Azwitamisi E.
    [J]. TECHNOLOGIES FOR OPTICAL COUNTERMEASURES IX, 2012, 8543
  • [4] USING OPEN-SOURCE NATURAL LANGUAGE PROCESSING TO CLASSIFY TRAUMATIC CRANIAL HEMORRHAGES
    Lopez, Alexander
    Crawford, Malcolm
    Tran, Diem Kieu
    Chen, Jefferson
    [J]. JOURNAL OF NEUROTRAUMA, 2021, 38 (14) : A83 - A83
  • [5] Open-source Natural Language Processing on the PAL Robotics ARI Social Robot
    Lemaignan, Severin
    Cooper, Sara
    Ros, Raquel
    Ferrini, Lorenzo
    Andriella, Antonio
    Irisarri, Aina
    [J]. COMPANION OF THE ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION, HRI 2023, 2023, : 907 - 908
  • [6] CAMeL Tools: An Open Source Python']Python Toolkit for Arabic Natural Language Processing
    Obeid, Ossama
    Zalmout, Nasser
    Khalifa, Salam
    Taji, Dima
    Oudah, Mai
    Alhafni, Bashar
    Inoue, Go
    Eryani, Fadhl
    Erdmann, Alexander
    Habash, Nizar
    [J]. PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2020), 2020, : 7022 - 7032
  • [7] CSLM - A modular Open-Source Continuous Space Language Modeling Toolkit
    Schwenk, Holger
    [J]. 14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 1197 - 1201
  • [8] BTK: An open-source toolkit for fetal brain MR image processing
    Rousseau, Francois
    Oubel, Estanislao
    Pontabry, Julien
    Schweitzer, Marc
    Studholme, Colin
    Koob, Meriam
    Dietemann, Jean-Louis
    [J]. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2013, 109 (01) : 65 - 73
  • [9] SIMPA: an open-source toolkit for simulation and image processing for photonics and acoustics
    Groehl, Janek
    Dreher, Kris K.
    Schellenberg, Melanie
    Rix, Tom
    Holzwarth, Niklas
    Vieten, Patricia
    Ayala, Leonardo
    Bohndiek, Sarah E.
    Seitel, Alexander
    Maier-Hein, Lena
    [J]. JOURNAL OF BIOMEDICAL OPTICS, 2022, 27 (08)
  • [10] Automated Radiology Report Summarization Using an Open-Source Natural Language Processing Pipeline
    Daniel J. Goff
    Thomas W. Loehfelm
    [J]. Journal of Digital Imaging, 2018, 31 : 185 - 192