Coder Social home page Coder Social logo

ammieqi / df-net Goto Github PK

View Code? Open in Web Editor NEW

This project forked from looperxx/df-net

0.0 2.0 0.0 48.64 MB

Open source code for ACL 2020 Paper "Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog"

Python 94.39% Perl 5.61%

df-net's Introduction

Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog

This repository contains the PyTorch implementation of the paper:

Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog. Libo Qin, Xiao Xu, Wanxiang Che, Yue Zhang, Ting Liu. ACL 2020. [PDF(Arxiv)]

If you use any source codes or the datasets included in this toolkit in your work, please cite the following paper. The bibtex are listed below:

......

contrast

In the following, we will guide you how to use this repository step by step.

Architecture

framework

Results

contrast

Preparation

Our code is based on PyTorch 1.2. Required python packages:

  • numpy==1.18.1
  • tqdm==4.32.1
  • torch==1.2.0

We highly suggest you using Anaconda to manage your python environment.

How to Run it

The script myTrain.py acts as a main function to the project, you can run the experiments by the following commands.

# SMD dataset
python myTrain.py -gpu=True -ds=kvr -dr=0.2 -bsz=16 -an=SMD -op=SMD.log
# MultiWOZ 2.1 dataset
python myTrain.py -gpu=True -ds=woz -dr=0.1 -bsz=32 -an=WOZ -op=WOZ.log

We also provide our reported model parameters in the save/best directory, you can run the following command to evaluate them and so on.

python myTrain.py -gpu=True -e=0 -ds=kvr -bsz=16 -path=save/best/SMD -op=SMD.log
python myTrain.py -gpu=True -e=0 -ds=woz -bsz=32 -path=save/best/MultiWOZ -op=WOZ.log

Due to some stochastic factors(e.g., GPU and environment), it maybe need to slightly tune the hyper-parameters using grid search to reproduce the results reported in our paper. All the hyper-parameters are in the utils/config.py and here are the suggested hyper-parameter settings:

  • Dropout ratio [0.1, 0.15, 0.2, 0.25, 0.3]
  • Batch size [16, 32]
  • Teacher forcing ratio [0.7, 0.8, 0.9, 1.0]

If you have any question, please issue the project or email me and we will reply you soon.

Acknowledgement

Global-to-local Memory Pointer Networks for Task-Oriented Dialogue. Chien-Sheng Wu, Richard Socher, Caiming Xiong. ICLR 2019. [PDF] [Open Reivew] [Code]

We are highly grateful for the public code of GLMP!

df-net's People

Contributors

looperxx avatar

Watchers

 avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.