Optimus: the first large-scale pre-trained VAE language model

Overview

Optimus: the first pre-trained Big VAE language model

This repository contains source code necessary to reproduce the results presented in the EMNLP 2020 paper Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space.

The network architecture of Optimus: encoder for representation learning and decoder for generation Sentences are organized and manipulated in a pre-trained compact and smooth latent space

For more on this project, see the Microsoft Research Blog post.

News

May 21, 2020: Releasing a demo for latent space manipulation, including sentence interpolation and analogy. Check out the website.

May 20, 2020: The latent space manipulation code is cleaned and released. See instructions at optimius_for_snli.md.

May 13, 2020: The fine-tuning code for langauge modeling is released. See instructions at optimus_finetune_language_models.md

Contents

There are four steps to use this codebase to reproduce the results in the paper.

  1. Dependencies
  2. Prepare datasets
  3. Model training
    1. Pre-training on setences in Wikipedia
    2. Languange Modeling
    3. Guided Language Generation
    4. Low-resource Language Understanding
  4. Collect and plot results

Dependencies

Pull docker from Docker Hub at: chunyl/pytorch-transformers:v2. Please see the instruction at doc/env.md

The project is organized into the following structures, with ensential files & folders visualized. output saves the models checkpoints.

├── Optimus
   └── code
       ├── examples
           ├── big_ae
               ├── modules
                   ├── vae.py
                   └── ...
               ├── run_lm_vae_pretraining_phdist_beta.py
               ├── run_lm_vae_training.py
               └── ...
	   ├── pytorch_transformers
               ├── modeling_bert.py
               ├── modeling_gpt2.py
               └── ...
       ├── scripts
           ├── scripts_docker
	   ├── scripts_local
	   ├── scripts_philly
   └── data
       └── datasets
           ├── wikipedia_json_64_filtered
               └── ...
	   ├── snli_data
           └── ...
   └── output
       ├── pretrain
       ├── LM
       └── ...       

Prepare Datasets

Please download or preparation the data via following the instructions at data/download_datasets.md.

Model Training

1. Pre-training on setences in Wikipedia

We pre-trained our models on Philly (a Microsoft internal compute cluster), the code is specialized for multi-node multi-GPU compute on this platform. The pre-training main python is run_lm_vae_pretraining_phdist_beta.py. You may need to adjust the distributed training scripts.

2. Languange Modeling

To have a fair comparison with existing VAE languange models, we consider a model with latent dimension 32. The pre-trained model is fine-tuned on four commonly datasets for one epoch. Please see the details at doc/optimus_finetune_language_models.md

3. Guided Language Generation

Latent Space Manipulation To ensure good performance, we consider a model with latent dimension 768. The pre-trained model is fine-tuned on SNLI dataset, where sentences show related patterns. Please see the details at Please see the details at doc/optimius_for_snli.md

4. Low-resource Language Understanding

Collect and Plot Results

Once the networks are trained and the results are saved, we extracted key results using Python script. The results can be plotted using the included IPython notebook plots/main_plots.ipynb. Start the IPython Notebook server:

$ cd plots
$ ipython notebook

Select the main_plots.ipynb notebook and execute the included code. Note that without modification, we have copyed our extracted results into the notebook, and script will output figures in the paper. If you've run your own training and wish to plot results, you'll have to organize your results in the same format instead.

Questions?

Please drop me (Chunyuan) a line if you have any questions.

@inproceedings{li2020_Optimus,
  title={Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space},
  author={Li, Chunyuan and Gao, Xiang and Li, Yuan and Li, Xiujun and Peng, Baolin and Zhang, Yizhe and Gao, Jianfeng},
  booktitle={EMNLP},
  year={2020}
}
Owner
Researcher @ Microsoft Research
This is the code for HOI Transformer

HOI Transformer Code for CVPR 2021 accepted paper End-to-End Human Object Interaction Detection with HOI Transformer. Reproduction We recomend you to

BigBangEpoch 124 Dec 29, 2022
PyTorch wrapper for Taichi data-oriented class

Stannum PyTorch wrapper for Taichi data-oriented class PRs are welcomed, please see TODOs. Usage from stannum import Tin import torch data_oriented =

86 Dec 23, 2022
Neural network chess engine trained on Gary Kasparov's games.

Neural Chess It's not the best chess engine, but it is a chess engine. Proof of concept neural network chess engine (feed-forward multi-layer perceptr

3 Jun 22, 2022
METER: Multimodal End-to-end TransformER

METER Code and pre-trained models will be publicized soon. Citation @article{dou2021meter, title={An Empirical Study of Training End-to-End Vision-a

Zi-Yi Dou 257 Jan 06, 2023
Official Implementation of DE-DETR and DELA-DETR in "Towards Data-Efficient Detection Transformers"

DE-DETRs By Wen Wang, Jing Zhang, Yang Cao, Yongliang Shen, and Dacheng Tao This repository is an official implementation of DE-DETR and DELA-DETR in

Wen Wang 61 Dec 12, 2022
Test-Time Personalization with a Transformer for Human Pose Estimation, NeurIPS 2021

Transforming Self-Supervision in Test Time for Personalizing Human Pose Estimation This is an official implementation of the NeurIPS 2021 paper: Trans

41 Nov 28, 2022
Pydantic models for pywttr and aiopywttr.

Pydantic models for pywttr and aiopywttr.

Almaz 2 Dec 08, 2022
A small fun project using python OpenCV, mediapipe, and pydirectinput

Here I tried a small fun project using python OpenCV, mediapipe, and pydirectinput. Here we can control moves car game when yellow color come to right box (press key 'd') left box (press key 'a') lef

Sameh Elisha 3 Nov 17, 2022
Source code release of the paper: Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation.

GNet-pose Project Page: http://guanghan.info/projects/guided-fractal/ UPDATE 9/27/2018: Prototxts and model that achieved 93.9Pck on LSP dataset. http

Guanghan Ning 83 Nov 21, 2022
Official implementation of deep-multi-trajectory-based single object tracking (IEEE T-CSVT 2021).

DeepMTA_PyTorch Officical PyTorch Implementation of "Dynamic Attention-guided Multi-TrajectoryAnalysis for Single Object Tracking", Xiao Wang, Zhe Che

Xiao Wang(王逍) 7 Dec 03, 2022
Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019

PoseNet of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image" Introduction This repo is official Py

Gyeongsik Moon 677 Dec 25, 2022
The 7th edition of NTIRE: New Trends in Image Restoration and Enhancement workshop will be held on June 2022 in conjunction with CVPR 2022.

NTIRE 2022 - Image Inpainting Challenge Important dates 2022.02.01: Release of train data (input and output images) and validation data (only input) 2

Andrés Romero 37 Nov 27, 2022
Inference code for "StylePeople: A Generative Model of Fullbody Human Avatars" paper. This code is for the part of the paper describing video-based avatars.

NeuralTextures This is repository with inference code for paper "StylePeople: A Generative Model of Fullbody Human Avatars" (CVPR21). This code is for

Visual Understanding Lab @ Samsung AI Center Moscow 18 Oct 06, 2022
The project covers common metrics for super-resolution performance evaluation.

Super-Resolution Performance Evaluation Code The project covers common metrics for super-resolution performance evaluation. Metrics support The script

xmy 10 Aug 03, 2022
Code for STFT Transformer used in BirdCLEF 2021 competition.

STFT_Transformer Code for STFT Transformer used in BirdCLEF 2021 competition. The STFT Transformer is a new way to use Transformers similar to Vision

Jean-François Puget 69 Sep 29, 2022
Deep Q Learning with OpenAI Gym and Pokemon Showdown

pokemon-deep-learning An openAI gym project for pokemon involving deep q learning. Made by myself, Sam Little, and Layton Webber. This code captures g

2 Dec 22, 2021
This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.

Pruning Self-attentions into Convolutional Layers in Single Path This is the official repository for our paper: Pruning Self-attentions into Convoluti

Zhuang AI Group 77 Dec 26, 2022
Geometric Vector Perceptrons --- a rotation-equivariant GNN for learning from biomolecular structure

Geometric Vector Perceptron Implementation of equivariant GVP-GNNs as described in Learning from Protein Structure with Geometric Vector Perceptrons b

Dror Lab 142 Dec 29, 2022
Machine Learning in Asset Management (by @firmai)

Machine Learning in Asset Management If you like this type of content then visit ML Quant site below: https://www.ml-quant.com/ Part One Follow this l

Derek Snow 1.5k Jan 02, 2023
CellRank's reproducibility repository.

CellRank's reproducibility repository We believe that reproducibility is key and have made it as simple as possible to reproduce our results. Please e

Theis Lab 8 Oct 08, 2022