Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System

Related tags

Deep Learningpptod
Overview

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System

Authors: Yixuan Su, Lei Shu, Elman Mansimov, Arshit Gupta, Deng Cai, Yi-An Lai, and Yi Zhang

Code our PPTOD paper: Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System

Introduction:

Pre-trained language models have been recently shown to benefit task-oriented dialogue (TOD) systems. Despite their success, existing methods often formulate this task as a cascaded generation problem which can lead to error accumulation across different sub-tasks and greater data annotation overhead. In this study, we present PPTOD, a unified model that seamlessly supports both task-oriented dialogue understanding and response generation in a plug-and-play fashion. In addition, we introduce a new dialogue multi-task pre-training strategy that allows the model to learn the primary TOD task completion skills from heterogeneous dialog corpora. We extensively test our model on three benchmark TOD tasks, including end-to-end dialogue modelling, dialogue state tracking, and intent classification. Results show that PPTOD creates new state-of-the-art on all evaluated tasks in both full training and low-resource scenarios. Furthermore, comparisons against previous SOTA methods show that the responses generated by PPTOD are more factually correct and semantically coherent as judged by human annotators.

Alt text

1. Citation

If you find our paper and resources useful, please kindly cite our paper:

  @article{su2021multitask,
    author    = {Yixuan Su and
                 Lei Shu and
                 Elman Mansimov and
                 Arshit Gupta and
                 Deng Cai and
                 Yi{-}An Lai and
                 Yi Zhang},
    title     = {Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System},
    journal   = {CoRR},
    volume    = {abs/2109.14739},
    year      = {2021},
    url       = {https://arxiv.org/abs/2109.14739},
    eprinttype = {arXiv},
    eprint    = {2109.14739}
  }

2. Environment Setup:

pip3 install -r requirements.txt
python -m spacy download en_core_web_sm

3. PPTOD Checkpoints:

You can download checkpoints of PPTOD with different configurations here.

PPTOD-small PPTOD-base PPTOD-large
here here here

To use PPTOD, you should download the checkpoint you want and unzip it in the ./checkpoints directory.

Alternatively, you can run the following commands to download the PPTOD checkpoints.

(1) Downloading Pre-trained PPTOD-small Checkpoint:

cd checkpoints
chmod +x ./download_pptod_small.sh
./download_pptod_small.sh

(2) Downloading Pre-trained PPTOD-base Checkpoint:

cd checkpoints
chmod +x ./download_pptod_base.sh
./download_pptod_base.sh

(3) Downloading Pre-trained PPTOD-large Checkpoint:

cd checkpoints
chmod +x ./download_pptod_large.sh
./download_pptod_large.sh

4. Data Preparation:

The detailed instruction for preparing the pre-training corpora and the data of downstream TOD tasks are provided in the ./data folder.

5. Dialogue Multi-Task Pre-training:

To pre-train a PPTOD model from scratch, please refer to details provided in ./Pretraining directory.

6. Benchmark TOD Tasks:

(1) End-to-End Dialogue Modelling:

To perform End-to-End Dialogue Modelling using PPTOD, please refer to details provided in ./E2E_TOD directory.

(2) Dialogue State Tracking:

To perform Dialogue State Tracking using PPTOD, please refer to details provided in ./DST directory.

(3) Intent Classification:

To perform Intent Classification using PPTOD, please refer to details provided in ./IC directory.

Security

See CONTRIBUTING for more information.

License

This project is licensed under the Apache-2.0 License.

Owner
Amazon Web Services - Labs
AWS Labs
Amazon Web Services - Labs
existing and custom freqtrade strategies supporting the new hyperstrategy format.

freqtrade-strategies Description Existing and self-developed strategies, rewritten to support the new HyperStrategy format from the freqtrade-develop

39 Aug 20, 2021
The official PyTorch code for 'DER: Dynamically Expandable Representation for Class Incremental Learning' accepted by CVPR2021

DER.ClassIL.Pytorch This repo is the official implementation of DER: Dynamically Expandable Representation for Class Incremental Learning (CVPR 2021)

rhyssiyan 108 Jan 01, 2023
HybVIO visual-inertial odometry and SLAM system

HybVIO A visual-inertial odometry system with an optional SLAM module. This is a research-oriented codebase, which has been published for the purposes

Spectacular AI 320 Jan 03, 2023
Nonnegative spatial factorization for multivariate count data

Nonnegative spatial factorization for multivariate count data This repository contains supporting code to facilitate reproducible analysis. For detail

Will Townes 24 Dec 19, 2022
The full training script for Enformer (Tensorflow Sonnet) on TPU clusters

Enformer TPU training script (wip) The full training script for Enformer (Tensorflow Sonnet) on TPU clusters, in an effort to migrate the model to pyt

Phil Wang 10 Oct 19, 2022
1st Solution For ICDAR 2021 Competition on Mathematical Formula Detection

This project releases our 1st place solution on ICDAR 2021 Competition on Mathematical Formula Detection. We implement our solution based on MMDetection, which is an open source object detection tool

yuxzho 94 Dec 25, 2022
Implementation of paper "Self-supervised Learning on Graphs:Deep Insights and New Directions"

SelfTask-GNN A PyTorch implementation of "Self-supervised Learning on Graphs: Deep Insights and New Directions". [paper] In this paper, we first deepe

Wei Jin 85 Oct 13, 2022
Datasets and source code for our paper Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach

Introduction Datasets and source code for our paper Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach Datasets: WebFG-496

21 Sep 30, 2022
使用深度学习框架提取视频硬字幕;docker容器免安装深度学习库,使用本地api接口使得界面和后端识别分离;

extract-video-subtittle 使用深度学习框架提取视频硬字幕; 本地识别无需联网; CPU识别速度可观; 容器提供API接口; 运行环境 本项目运行环境非常好搭建,我做好了docker容器免安装各种深度学习包; 提供windows界面操作; 容器为CPU版本; 视频演示 https

歌者 16 Aug 06, 2022
A PyTorch implementation of "Graph Wavelet Neural Network" (ICLR 2019)

Graph Wavelet Neural Network ⠀⠀ A PyTorch implementation of Graph Wavelet Neural Network (ICLR 2019). Abstract We present graph wavelet neural network

Benedek Rozemberczki 490 Dec 16, 2022
An University Project of Quera Web Crawling.

WebCrawlerProject An University Project of Quera Web Crawling. خزشگر اینستاگرام در این پروژه شما باید با استفاده از کتابخانه های زیر یک خزشگر اینستاگر

Mahdi 3 Aug 12, 2022
Official repository for the paper "GN-Transformer: Fusing AST and Source Code information in Graph Networks".

GN-Transformer AST This is the official repository for the paper "GN-Transformer: Fusing AST and Source Code information in Graph Networks". Data Prep

Cheng Jun-Yan 10 Nov 26, 2022
Implement of homography net by pytorch

HomographyNet Implement of homography net by pytorch Brief Introduction This project is based on the work Homography-Net: @article{detone2016deep, t

ronghao_CN 4 May 19, 2022
A learning-based data collection tool for human segmentation

FullBodyFilter A Learning-Based Data Collection Tool For Human Segmentation Contents Documentation Source Code and Scripts Overview of Project Usage O

Robert Jiang 4 Jun 24, 2022
Code repository for "Reducing Underflow in Mixed Precision Training by Gradient Scaling" presented at IJCAI '20

Reducing Underflow in Mixed Precision Training by Gradient Scaling This project implements the gradient scaling method to improve the performance of m

Ruizhe Zhao 5 Apr 14, 2022
[ICCV2021] Official Pytorch implementation for SDGZSL (Semantics Disentangling for Generalized Zero-Shot Learning)

Semantics Disentangling for Generalized Zero-shot Learning This is the official implementation for paper Zhi Chen, Yadan Luo, Ruihong Qiu, Zi Huang, J

25 Dec 06, 2022
Efficient Two-Step Networks for Temporal Action Segmentation (Neurocomputing 2021)

Efficient Two-Step Networks for Temporal Action Segmentation This repository provides a PyTorch implementation of the paper Efficient Two-Step Network

8 Apr 16, 2022
Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models.

Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models

AdvBox 1.3k Dec 25, 2022
Solution to the Weather4cast 2021 challenge

This code was used for the entry by the team "antfugue" for the Weather4cast 2021 Challenge. Below, you can find the instructions for generating predi

Jussi Leinonen 13 Jan 03, 2023
Wordle Env: A Daily Word Environment for Reinforcement Learning

Wordle Env: A Daily Word Environment for Reinforcement Learning Setup Steps: git pull [email&#

2 Mar 28, 2022