Multi-Task Deep Neural Networks for Natural Language Understanding

Overview

License: MIT Travis-CI

New Release
We released Adversarial training for both LM pre-training/finetuning and f-divergence.

Large-scale Adversarial training for LMs: ALUM code.
If you want to use the old version, please use following cmd to clone the code:
git clone -b v0.1 https://github.com/namisan/mt-dnn.git

Multi-Task Deep Neural Networks for Natural Language Understanding

This PyTorch package implements the Multi-Task Deep Neural Networks (MT-DNN) for Natural Language Understanding, as described in:

Xiaodong Liu*, Pengcheng He*, Weizhu Chen and Jianfeng Gao
Multi-Task Deep Neural Networks for Natural Language Understanding
ACL 2019
*: Equal contribution

Xiaodong Liu, Pengcheng He, Weizhu Chen and Jianfeng Gao
Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding
arXiv version

Pengcheng He, Xiaodong Liu, Weizhu Chen and Jianfeng Gao
Hybrid Neural Network Model for Commonsense Reasoning
arXiv version

Liyuan Liu, Haoming Jiang, Pengcheng He, Weizhu Chen, Xiaodong Liu, Jianfeng Gao and Jiawei Han
On the Variance of the Adaptive Learning Rate and Beyond
arXiv version

Haoming Jiang, Pengcheng He, Weizhu Chen, Xiaodong Liu, Jianfeng Gao and Tuo Zhao
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization
arXiv version

Xiaodong Liu, Yu Wang, Jianshu Ji, Hao Cheng, Xueyun Zhu, Emmanuel Awa, Pengcheng He, Weizhu Chen, Hoifung Poon, Guihong Cao, Jianfeng Gao
The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding
arXiv version

Xiaodong Liu, Hao Cheng, Pengcheng He, Weizhu Chen, Yu Wang, Hoifung Poon and Jianfeng Gao
Adversarial Training for Large Neural Language Models
arXiv version

Hao Cheng and Xiaodong Liu and Lis Pereira and Yaoliang Yu and Jianfeng Gao
Posterior Differential Regularization with f-divergence for Improving Model Robustness
arXiv version

Quickstart

Setup Environment

Install via pip:

  1. python3.6
    Reference to download and install : https://www.python.org/downloads/release/python-360/

  2. install requirements
    > pip install -r requirements.txt

Use docker:

  1. Pull docker
    > docker pull allenlao/pytorch-mt-dnn:v0.5

  2. Run docker
    > docker run -it --rm --runtime nvidia allenlao/pytorch-mt-dnn:v1.2 bash
    Please refer to the following link if you first use docker: https://docs.docker.com/

Train a toy MT-DNN model

  1. Download data
    > sh download.sh
    Please refer to download GLUE dataset: https://gluebenchmark.com/

  2. Preprocess data
    > sh experiments/glue/prepro.sh

  3. Training
    > python train.py

Note that we ran experiments on 4 V100 GPUs for base MT-DNN models. You may need to reduce batch size for other GPUs.

GLUE Result reproduce

  1. MTL refinement: refine MT-DNN (shared layers), initialized with the pre-trained BERT model, via MTL using all GLUE tasks excluding WNLI to learn a new shared representation.
    Note that we ran this experiment on 8 V100 GPUs (32G) with a batch size of 32.

    • Preprocess GLUE data via the aforementioned script
    • Training:
      >scripts\run_mt_dnn.sh
  2. Finetuning: finetune MT-DNN to each of the GLUE tasks to get task-specific models.
    Here, we provide two examples, STS-B and RTE. You can use similar scripts to finetune all the GLUE tasks.

    • Finetune on the STS-B task
      > scripts\run_stsb.sh
      You should get about 90.5/90.4 on STS-B dev in terms of Pearson/Spearman correlation.
    • Finetune on the RTE task
      > scripts\run_rte.sh
      You should get about 83.8 on RTE dev in terms of accuracy.

SciTail & SNIL Result reproduce (Domain Adaptation)

  1. Domain Adaptation on SciTail
    >scripts\scitail_domain_adaptation_bash.sh

  2. Domain Adaptation on SNLI
    >scripts\snli_domain_adaptation_bash.sh

Sequence Labeling Task

  1. Preprocess data
    a) Download NER data to data/ner including: {train/valid/test}.txt
    b) Convert NER data to the canonical format: > python experiments\ner\prepro.py --data data\ner --output_dir data\canonical_data
    c) Preprocess the canonical data to the MT-DNN format: > python prepro_std.py --root_dir data\canonical_data --task_def experiments\ner\ner_task_def.yml --model bert-base-uncased

  2. Training
    > python train.py --data_dir <data-path> --init_checkpoint <bert-base-uncased> --train_dataset squad,squad-v2 --test_dataset squad,squad-v2 --task_def experiments\squad\squad_task_def.yml

Question Answer Task

  1. Preprocess data
    a) Download SQuAD data to data/squad including: {train/valid}.txt and then change file name to: {squad_train/squad_dev}.json
    b) Convert data to the MT-DNN format: > python experiments\squad\squad_prepro.py --root_dir data\canonical_data --task_def experiments\squad\squad_task_def.yml --model bert-base-uncased

  2. Training
    > python train.py --data_dir <data-path> --init_checkpoint <bert-model> --train_dataset ner --test_dataset ner --task_def experiments\ner\ner_task_def.yml

SMART

Adv training at the fine-tuning stages: > python train.py --data_dir <data-path> --init_checkpoint <bert/mt-dnn-model> --train_dataset mnli --test_dataset mnli_matched,mnli_mismatched --task_def experiments\glue\glue_task_def.yml --adv_train --adv_opt 1

HNN

The code to reproduce HNN is under hnn folder, to reproduce the results of HNN, run

> hnn/script/hnn_train_large.sh

Extract embeddings

  1. Extracting embeddings of a pair text example
    >python extractor.py --do_lower_case --finput input_examples\pair-input.txt --foutput input_examples\pair-output.json --bert_model bert-base-uncased --checkpoint mt_dnn_models\mt_dnn_base.pt
    Note that the pair of text is split by a special token |||. You may refer input_examples\pair-output.json as example.

  2. Extracting embeddings of a single sentence example
    >python extractor.py --do_lower_case --finput input_examples\single-input.txt --foutput input_examples\single-output.json --bert_model bert-base-uncased --checkpoint mt_dnn_models\mt_dnn_base.pt

Speed up Training

  1. Gradient Accumulation
    If you have small GPUs, you may need to use the gradient accumulation to make training stable.
    For example, if you use the flag: --grad_accumulation_step 4 during the training, the actual batch size will be batch_size * 4.

  2. FP16 The current version of MT-DNN also supports FP16 training, and please install apex.
    You just need to turn on the flag during the training: --fp16
    Please refer the script: scripts\run_mt_dnn_gc_fp16.sh

Convert Tensorflow BERT model to the MT-DNN format

Here, we go through how to convert a Chinese Tensorflow BERT model into mt-dnn format.

  1. Download BERT model from the Google bert web: https://github.com/google-research/bert

  2. Run the following script for MT-DNN format
    python scripts\convert_tf_to_pt.py --tf_checkpoint_root chinese_L-12_H-768_A-12\ --pytorch_checkpoint_path chinese_L-12_H-768_A-12\bert_base_chinese.pt

TODO

  • Publish pretrained Tensorflow checkpoints.

FAQ

Did you share the pretrained mt-dnn models?

Yes, we released the pretrained shared embedings via MTL which are aligned to BERT base/large models: mt_dnn_base.pt and mt_dnn_large.pt.
To obtain the similar models:

  1. run the >sh scripts\run_mt_dnn.sh, and then pick the best checkpoint based on the average dev preformance of MNLI/RTE.
  2. strip the task-specific layers via scritps\strip_model.py.

Why SciTail/SNLI do not enable SAN?

For SciTail/SNLI tasks, the purpose is to test generalization of the learned embedding and how easy it is adapted to a new domain instead of complicated model structures for a direct comparison with BERT. Thus, we use a linear projection on the all domain adaptation settings.

What is the difference between V1 and V2

The difference is in the QNLI dataset. Please refere to the GLUE official homepage for more details. If you want to formulate QNLI as pair-wise ranking task as our paper, make sure that you use the old QNLI data.
Then run the prepro script with flags: > sh experiments/glue/prepro.sh --old_glue
If you have issues to access the old version of the data, please contact the GLUE team.

Did you fine-tune single task for your GLUE leaderboard submission?

We can use the multi-task refinement model to run the prediction and produce a reasonable result. But to achieve a better result, it requires a fine-tuneing on each task. It is worthing noting the paper in arxiv is a littled out-dated and on the old GLUE dataset. We will update the paper as we mentioned below.

Notes and Acknowledgments

BERT pytorch is from: https://github.com/huggingface/pytorch-pretrained-BERT
BERT: https://github.com/google-research/bert
We also used some code from: https://github.com/kevinduh/san_mrc

Related Projects/Codebase

  1. Pretrained UniLM: https://github.com/microsoft/unilm
  2. Pretrained Response Generation Model: https://github.com/microsoft/DialoGPT
  3. Internal MT-DNN repo: https://github.com/microsoft/mt-dnn

How do I cite MT-DNN?

@inproceedings{liu2019mt-dnn,
    title = "Multi-Task Deep Neural Networks for Natural Language Understanding",
    author = "Liu, Xiaodong and He, Pengcheng and Chen, Weizhu and Gao, Jianfeng",
    booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/P19-1441",
    pages = "4487--4496"
}


@article{liu2019mt-dnn-kd,
  title={Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding},
  author={Liu, Xiaodong and He, Pengcheng and Chen, Weizhu and Gao, Jianfeng},
  journal={arXiv preprint arXiv:1904.09482},
  year={2019}
}


@article{he2019hnn,
  title={A Hybrid Neural Network Model for Commonsense Reasoning},
  author={He, Pengcheng and Liu, Xiaodong and Chen, Weizhu and Gao, Jianfeng},
  journal={arXiv preprint arXiv:1907.11983},
  year={2019}
}


@article{liu2019radam,
  title={On the Variance of the Adaptive Learning Rate and Beyond},
  author={Liu, Liyuan and Jiang, Haoming and He, Pengcheng and Chen, Weizhu and Liu, Xiaodong and Gao, Jianfeng and Han, Jiawei},
  journal={arXiv preprint arXiv:1908.03265},
  year={2019}
}


@article{jiang2019smart,
  title={SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization},
  author={Jiang, Haoming and He, Pengcheng and Chen, Weizhu and Liu, Xiaodong and Gao, Jianfeng and Zhao, Tuo},
  journal={arXiv preprint arXiv:1911.03437},
  year={2019}
}


@article{liu2020mtmtdnn,
  title={The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding},
  author={Liu, Xiaodong and Wang, Yu and Ji, Jianshu and Cheng, Hao and Zhu, Xueyun and Awa, Emmanuel and He, Pengcheng and Chen, Weizhu and Poon, Hoifung and Cao, Guihong and Jianfeng Gao},
  journal={arXiv preprint arXiv:2002.07972},
  year={2020}
}


@article{liu2020alum,
  title={Adversarial Training for Large Neural Language Models},
  author={Liu, Xiaodong and Cheng, Hao and He, Pengcheng and Chen, Weizhu and Wang, Yu and Poon, Hoifung and Gao, Jianfeng},
  journal={arXiv preprint arXiv:2004.08994},
  year={2020}
}

@article{cheng2020posterior,
  title={Posterior Differential Regularization with f-divergence for Improving Model Robustness},
  author={Cheng, Hao and Liu, Xiaodong and Pereira, Lis and Yu, Yaoliang and Gao, Jianfeng},
  journal={arXiv preprint arXiv:2010.12638},
  year={2020}
}

Contact Information

For help or issues using MT-DNN, please submit a GitHub issue.

For personal communication related to this package, please contact Xiaodong Liu ([email protected]), Yu Wang ([email protected]), Pengcheng He ([email protected]), Weizhu Chen ([email protected]), Jianshu Ji ([email protected]), Hao Cheng ([email protected]) or Jianfeng Gao ([email protected]).

Owner
Xiaodong
And if you gaze long into an abyss, the abyss also gazes into you --Friedrich Nietzsche
Xiaodong
Self-Supervised Deep Blind Video Super-Resolution

Self-Blind-VSR Paper | Discussion Self-Supervised Deep Blind Video Super-Resolution By Haoran Bai and Jinshan Pan Abstract Existing deep learning-base

Haoran Bai 35 Dec 09, 2022
BOVText: A Large-Scale, Multidimensional Multilingual Dataset for Video Text Spotting

BOVText: A Large-Scale, Bilingual Open World Dataset for Video Text Spotting Updated on December 10, 2021 (Release all dataset(2021 videos)) Updated o

weijiawu 47 Dec 26, 2022
Lightwood is Legos for Machine Learning.

Lightwood is like Legos for Machine Learning. A Pytorch based framework that breaks down machine learning problems into smaller blocks that can be glu

MindsDB Inc 312 Jan 08, 2023
Python implementation of "Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation"

MIPNet: Multi-Instance Pose Networks This repository is the official pytorch python implementation of "Multi-Instance Pose Networks: Rethinking Top-Do

Rawal Khirodkar 57 Dec 12, 2022
Code for the submitted paper Surrogate-based cross-correlation for particle image velocimetry

Surrogate-based cross-correlation (SBCC) This repository contains code for the submitted paper Surrogate-based cross-correlation for particle image ve

5 Jun 30, 2022
Tensorflow2.0 🍎🍊 is delicious, just eat it! 😋😋

How to eat TensorFlow2 in 30 days ? 🔥 🔥 Click here for Chinese Version(中文版) 《10天吃掉那只pyspark》 🚀 github项目地址: https://github.com/lyhue1991/eat_pyspark

lyhue1991 9.7k Jan 01, 2023
DanceTrack: Multiple Object Tracking in Uniform Appearance and Diverse Motion

DanceTrack DanceTrack is a benchmark for tracking multiple objects in uniform appearance and diverse motion. DanceTrack provides box and identity anno

260 Dec 28, 2022
Repo for CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning

CReST in Tensorflow 2 Code for the paper: "CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning" by Chen Wei, Ki

Google Research 75 Nov 01, 2022
RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

RMNet: Equivalently Removing Residual Connection from Networks This repository is the official implementation of "RMNet: Equivalently Removing Residua

184 Jan 04, 2023
Dilated Convolution for Semantic Image Segmentation

Multi-Scale Context Aggregation by Dilated Convolutions Introduction Properties of dilated convolution are discussed in our ICLR 2016 conference paper

Fisher Yu 764 Dec 26, 2022
[NeurIPS 2019] Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss Kaidi Cao, Colin Wei, Adrien Gaidon, Nikos Arechiga, Tengyu Ma This is the offi

Kaidi Cao 528 Jan 01, 2023
Code for the paper "Next Generation Reservoir Computing"

Next Generation Reservoir Computing This is the code for the results and figures in our paper "Next Generation Reservoir Computing". They are written

OSU QuantInfo Lab 105 Dec 20, 2022
COVID-Net Open Source Initiative

The COVID-Net models provided here are intended to be used as reference models that can be built upon and enhanced as new data becomes available

Linda Wang 1.1k Dec 26, 2022
This code provides various models combining dilated convolutions with residual networks

Overview This code provides various models combining dilated convolutions with residual networks. Our models can achieve better performance with less

Fisher Yu 1.1k Dec 30, 2022
Principled Detection of Out-of-Distribution Examples in Neural Networks

ODIN: Out-of-Distribution Detector for Neural Networks This is a PyTorch implementation for detecting out-of-distribution examples in neural networks.

189 Nov 29, 2022
Official repo for the work titled "SharinGAN: Combining Synthetic and Real Data for Unsupervised GeometryEstimation"

SharinGAN Official repo for the work titled "SharinGAN: Combining Synthetic and Real Data for Unsupervised GeometryEstimation" The official project we

Koutilya PNVR 23 Oct 19, 2022
This is an official implementation for "ResT: An Efficient Transformer for Visual Recognition".

ResT By Qing-Long Zhang and Yu-Bin Yang [State Key Laboratory for Novel Software Technology at Nanjing University] This repo is the official implement

zhql 222 Dec 13, 2022
EMNLP 2021 - Frustratingly Simple Pretraining Alternatives to Masked Language Modeling

Frustratingly Simple Pretraining Alternatives to Masked Language Modeling This is the official implementation for "Frustratingly Simple Pretraining Al

Atsuki Yamaguchi 31 Nov 18, 2022
Collection of tasks for fast prototyping, baselining, finetuning and solving problems with deep learning.

Collection of tasks for fast prototyping, baselining, finetuning and solving problems with deep learning Installation

Pytorch Lightning 1.6k Jan 08, 2023
Cross-modal Retrieval using Transformer Encoder Reasoning Networks (TERN). With use of Metric Learning and FAISS for fast similarity search on GPU

Cross-modal Retrieval using Transformer Encoder Reasoning Networks This project reimplements the idea from "Transformer Reasoning Network for Image-Te

Minh-Khoi Pham 5 Nov 05, 2022