Must-read papers on improving efficiency for pre-trained language models.

Awesome Efficient PLM Papers

Must-read papers on improving efficiency for pre-trained language models.

The paper list is mainly mantained by Lei Li and Shuhuai Ren.

Knowledge Distillation

  1. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter NeurIPS workshop

    Victor Sanh, Lysandre Debut, Julien Chaumond, Thomas Wolf [pdf] [project]

  2. Patient Knowledge Distillation for BERT Model Compression EMNLP 2019

    Siqi Sun, Yu Cheng, Zhe Gan, Jingjing Liu [pdf] [project]

  3. Well-Read Students Learn Better: On the Importance of Pre-training Compact Models Preprint

    Iulia Turc, Ming-Wei Chang, Kenton Lee, Kristina Toutanova [pdf] [project]

  4. TinyBERT: Distilling BERT for Natural Language Understanding Findings of EMNLP 2020

    Xiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen, Linlin Li, Fang Wang, Qun Liu [pdf] [project]

  5. BERT-of-Theseus: Compressing BERT by Progressive Module Replacing EMNLP 2020

    Canwen Xu, Wangchunshu Zhou, Tao Ge, Furu Wei, Ming Zhou [pdf] [project]

  6. MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers NeurIPS 2020

    Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, Ming Zhou [pdf] [project]

  7. BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover's Distance EMNLP 2020

    Jianquan Li, Xiaokang Liu, Honghong Zhao, Ruifeng Xu, Min Yang, Yaohong Jin [pdf] [project]

  8. MixKD: Towards Efficient Distillation of Large-scale Language Models ICLR 2021

    Kevin J Liang, Weituo Hao, Dinghan Shen, Yufan Zhou, Weizhu Chen, Changyou Chen, Lawrence Carin [pdf]

  9. Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains ACL-IJCNLP 2021

    Haojie Pan, Chengyu Wang, Minghui Qiu, Yichang Zhang, Yaliang Li, Jun Huang [pdf]

  10. MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation ACL-IJCNLP 2021

    Ahmad Rashid, Vasileios Lioutas, Mehdi Rezagholizadeh [pdf]

  11. Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor ACL-IJCNLP 2021

    Xinyu Wang, Yong Jiang, Zhaohui Yan, Zixia Jia, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu [pdf] [project]

  12. Weight Distillation: Transferring the Knowledge in Neural Network Parameters ACL-IJCNLP 2021

    Ye Lin, Yanyang Li, Ziyang Wang, Bei Li, Quan Du, Tong Xiao, Jingbo Zhu [pdf]

  13. Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation ACL-IJCNLP 2021

    Yuanxin Liu, Fandong Meng, Zheng Lin, Weiping Wang, Jie Zhou [pdf]

  14. MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers Findings of ACL-IJCNLP 2021

    Wenhui Wang, Hangbo Bao, Shaohan Huang, Li Dong, Furu Wei [pdf] [project]

  15. One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers Findings of ACL-IJCNLP 2021

    Chuhan Wu, Fangzhao Wu, Yongfeng Huang [pdf]

Dynamic Early Exiting

  1. DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference ACL 2020

    Ji Xin, Raphael Tang, Jaejun Lee, Yaoliang Yu, Jimmy Lin [pdf] [project]

  2. FastBERT: a Self-distilling BERT with Adaptive Inference Time ACL 2020

    Weijie Liu, Peng Zhou, Zhe Zhao, Zhiruo Wang, Haotang Deng, Qi Ju [pdf] [project]

  3. The Right Tool for the Job: Matching Model and Instance Complexities ACL 2020

    Roy Schwartz, Gabriel Stanovsky, Swabha Swayamdipta, Jesse Dodge, Noah A. Smith [pdf] [project]

  4. A Global Past-Future Early Exit Method for Accelerating Inference of Pre-trained Language Models NAACL 2021

    Kaiyuan Liao, Yi Zhang, Xuancheng Ren, Qi Su, Xu Sun, Bin He [pdf] [project]

  5. CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade Preprint

    Lei Li, Yankai Lin, Deli Chen, Shuhuai Ren, Peng Li, Jie Zhou, Xu Sun [pdf] [project]

  6. Early Exiting BERT for Efficient Document Ranking SustaiNLP 2020

    Ji Xin, Rodrigo Nogueira, Yaoliang Yu, and Jimmy Lin [pdf] [project]

  7. BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression EACL 2021

    Ji Xin, Raphael Tang, Yaoliang Yu, and Jimmy Lin [pdf] [project]

  8. Accelerating BERT Inference for Sequence Labeling via Early-Exit ACL 2021

    Xiaonan Li, Yunfan Shao, Tianxiang Sun, Hang Yan, Xipeng Qiu, Xuanjing Huang [pdf] [project]

  9. BERT Loses Patience: Fast and Robust Inference with Early Exit NeurIPS 2020

    Wangchunshu Zhou, Canwen Xu, Tao Ge, Julian McAuley, Ke Xu, Furu Wei [pdf] [project]

  10. Early Exiting with Ensemble Internal Classifiers Preprint

    Tianxiang Sun, Yunhua Zhou, Xiangyang Liu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu [pdf]

Quantization

  1. Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT AAAI 2020

    Sheng Shen, Zhen Dong, Jiayu Ye, Linjian Ma, Zhewei Yao, Amir Gholami, Michael W. Mahoney, Kurt Keutzer [pdf] [project]

  2. TernaryBERT: Distillation-aware Ultra-low Bit BERT EMNLP 2020

    Wei Zhang, Lu Hou, Yichun Yin, Lifeng Shang, Xiao Chen, Xin Jiang, Qun Liu [pdf] [project]

  3. Q8BERT: Quantized 8Bit BERT NeurIPS 2019 Workshop

    Ofir Zafrir, Guy Boudoukh, Peter Izsak, Moshe Wasserblat [pdf] [project]

  4. BinaryBERT: Pushing the Limit of BERT Quantization EMNLP 2020

    Haoli Bai, Wei Zhang, Lu Hou, Lifeng Shang, Jing Jin, Xin Jiang, Qun Liu, Michael Lyu, Irwin King [pdf] [project]

  5. I-BERT: Integer-only BERT Quantization ICML 2021

    Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer [pdf] [project]

Pruning

  1. Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned ACL 2019

    Elena Voita, David Talbot, Fedor Moiseev, Rico Sennrich, Ivan Titov [pdf] [project]

  2. Are Sixteen Heads Really Better than One? NeurIPS 2019

    Paul Michel, Omer Levy, Graham Neubig [pdf] [project]

  3. The Lottery Ticket Hypothesis for Pre-trained BERT Networks NeurIPS 2020

    Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Zhangyang Wang, Michael Carbin [pdf] [project]

  4. Movement Pruning: Adaptive Sparsity by Fine-Tuning NeurIPS 2020

    Victor Sanh, Thomas Wolf, Alexander M. Rush [pdf] [project]

  5. Reducing Transformer Depth on Demand with Structured Dropout Preprint

    Angela Fan, Edouard Grave, Armand Joulin [pdf]

  6. When BERT Plays the Lottery, All Tickets Are Winning EMNLP 2020

    Sai Prasanna, Anna Rogers, Anna Rumshisky [pdf] [project]

  7. Structured Pruning of a BERT-based Question Answering Model Preprint

    J.S. McCarley, Rishav Chakravarti, Avirup Sil [pdf]

  8. Structured Pruning of Large Language Models EMNLP 2020

    Ziheng Wang, Jeremy Wohlwend, Tao Lei [pdf] [project]

  9. Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm NAACL 2021

    Dongkuan Xu, Ian E.H. Yen, Jinxi Zhao, Zhibin Xiao [pdf]

  10. Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization ACL 2021

    Chen Liang, Simiao Zuo, Minshuo Chen, Haoming Jiang, Xiaodong Liu, Pengcheng He, Tuo Zhao, Weizhu Chen [pdf] [project]

Contribution

If you find any related work not included in the list, do not hesitate to raise a PR to help us complete the list.

Owner
Tobias Lee
On the way becoming an NLPer.
Tobias Lee
Similar Resources

TweebankNLP - Pre-trained Tweet NLP Pipeline (NER, tokenization, lemmatization, POS tagging, dependency parsing) + Models + Tweebank-NER

TweebankNLP This repo contains the new Tweebank-NER dataset and Twitter-Stanza p

Jul 28, 2022

InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective

InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective This is the official code base for our ICLR 2021 paper

Jun 29, 2022

Unsupervised text tokenizer focused on computational efficiency

YouTokenToMe YouTokenToMe is an unsupervised text tokenizer focused on computational efficiency. It currently implements fast Byte Pair Encoding (BPE)

Aug 1, 2022

Unsupervised text tokenizer focused on computational efficiency

YouTokenToMe YouTokenToMe is an unsupervised text tokenizer focused on computational efficiency. It currently implements fast Byte Pair Encoding (BPE)

Feb 18, 2021

TunBERT is the first release of a pre-trained BERT model for the Tunisian dialect using a Tunisian Common-Crawl-based dataset.

TunBERT is the first release of a pre-trained BERT model for the Tunisian dialect using a Tunisian Common-Crawl-based dataset.

TunBERT is the first release of a pre-trained BERT model for the Tunisian dialect using a Tunisian Common-Crawl-based dataset. TunBERT was applied to three NLP downstream tasks: Sentiment Analysis (SA), Tunisian Dialect Identification (TDI) and Reading Comprehension Question-Answering (RCQA)

Jun 10, 2022

Google and Stanford University released a new pre-trained model called ELECTRA

Google and Stanford University released a new pre-trained model called ELECTRA

Google and Stanford University released a new pre-trained model called ELECTRA, which has a much compact model size and relatively competitive performance compared to BERT and its variants. For further accelerating the research of the Chinese pre-trained model, the Joint Laboratory of HIT and iFLYTEK Research (HFL) has released the Chinese ELECTRA models based on the official code of ELECTRA. ELECTRA-small could reach similar or even higher scores on several NLP tasks with only 1/10 parameters compared to BERT and its variants.

Jul 31, 2022

Code for CodeT5: a new code-aware pre-trained encoder-decoder model.

Code for CodeT5: a new code-aware pre-trained encoder-decoder model.

CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation This is the official PyTorch implementation

Aug 6, 2022

Use PaddlePaddle to reproduce the paper:mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer

Use PaddlePaddle to reproduce the paper:mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer

MT5_paddle Use PaddlePaddle to reproduce the paper:mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer English | 简体中文 mT5: A Massively

Oct 17, 2021

ElasticBERT: A pre-trained model with multi-exit transformer architecture.

This repository contains finetuning code and checkpoints for ElasticBERT. Towards Efficient NLP: A Standard Evaluation and A Strong Baseli

Jul 22, 2022
RoNER is a Named Entity Recognition model based on a pre-trained BERT transformer model trained on RONECv2

RoNER RoNER is a Named Entity Recognition model based on a pre-trained BERT transformer model trained on RONECv2. It is meant to be an easy to use, hi

Apr 28, 2022
The repository for the paper: Multilingual Translation via Grafting Pre-trained Language Models

Graformer The repository for the paper: Multilingual Translation via Grafting Pre-trained Language Models Graformer (also named BridgeTransformer in t

Jul 29, 2022
Prompt-learning is the latest paradigm to adapt pre-trained language models (PLMs) to downstream NLP tasks
Prompt-learning is the latest paradigm to adapt pre-trained language models (PLMs) to downstream NLP tasks

Prompt-learning is the latest paradigm to adapt pre-trained language models (PLMs) to downstream NLP tasks, which modifies the input text with a textual template and directly uses PLMs to conduct pre-trained tasks. This library provides a standard, flexible and extensible framework to deploy the prompt-learning pipeline. OpenPrompt supports loading PLMs directly from huggingface transformers. In the future, we will also support PLMs implemented by other libraries.

Aug 2, 2022
Chinese Pre-Trained Language Models (CPM-LM) Version-I

CPM-Generate 为了促进中文自然语言处理研究的发展,本项目提供了 CPM-LM (2.6B) 模型的文本生成代码,可用于文本生成的本地测试,并以此为基础进一步研究零次学习/少次学习等场景。[项目首页] [模型下载] [技术报告] 若您想使用CPM-1进行推理,我们建议使用高效推理工具BMI

Aug 6, 2022
PyTorch Implementation of "Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging" (Findings of ACL 2022)

Feature_CRF_AE Feature_CRF_AE provides a implementation of Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging

Apr 29, 2022
Guide to using pre-trained large language models of source code
Guide to using pre-trained large language models of source code

Large Models of Source Code I occasionally train and publicly release large neural language models on programs, including PolyCoder. Here, I describe

Jul 28, 2022
Silero Models: pre-trained speech-to-text, text-to-speech models and benchmarks made embarrassingly simple
Silero Models: pre-trained speech-to-text, text-to-speech models and benchmarks made embarrassingly simple

Silero Models: pre-trained speech-to-text, text-to-speech models and benchmarks made embarrassingly simple

Aug 6, 2022
DziriBERT: a Pre-trained Language Model for the Algerian Dialect
DziriBERT: a Pre-trained Language Model for the Algerian Dialect

DziriBERT is the first Transformer-based Language Model that has been pre-trained specifically for the Algerian Dialect.

Jul 28, 2022
Implementation of Natural Language Code Search in the project CodeBERT: A Pre-Trained Model for Programming and Natural Languages.

CodeBERT-Implementation In this repo we have replicated the paper CodeBERT: A Pre-Trained Model for Programming and Natural Languages. We are interest

Jul 1, 2022
Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper

Data Augmentation using Pre-trained Transformer Models Code associated with the Data Augmentation using Pre-trained Transformer Models paper Code cont

Aug 3, 2022