Coder Social home page Coder Social logo

jiahuan-pei / multiwoz-mdrg Goto Github PK

View Code? Open in Web Editor NEW
2.0 3.0 1.0 3.08 MB

The source code for paper "Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation"

Python 99.86% Shell 0.14%
ecai2020 task-oriented-dialogues dialogue-generation

multiwoz-mdrg's Introduction

RPMOG

To facilitate reproducibility, we release the source code for paper "Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation" on ECAI 2020.

Please contact me by email ([email protected]) if any questions and cite our paper if you use any resources and/or codes in this repository.

Requirements

Python 3 with pip

Quick start

In repo directory:

Install the required packages

  • Using Conda:
cd multiwoz-mdrg
conda create --name multiwoz python=3.7 anaconda
source activate multiwoz
conda install --file requirements.txt 
conda install pytorch torchvision -c pytorch

Preprocessing

To download and pre-process the data run:

python multiwoz/Create_delex_data.py

For debugging

To debug train.py, you can add the following parameteres to save time --debug=True --emb_size=5 --hid_size_dec=5 --hid_size_enc=5 --hid_size_pol=5 --max_epochs=2

To debug test.py, the parameters are: --debug=True --no_models=2 --beam_width=2

Training

To train the model run:

python train.py [--args=value]

Some of these args include:

// hyperparamters for model learning
--max_epochs        : numbers of epochs
--batch_size        : numbers of turns per batch
--lr_rate           : initial learning rate
--clip              : size of clipping
--l2_norm           : l2-regularization weight
--dropout           : dropout rate
--optim             : optimization method

// network structure
--emb_size          : word vectors emedding size
--use_attn          : whether to use attention
--hid_size_enc      : size of RNN hidden cell
--hid_size_pol      : size of policy hidden output
--hid_size_dec      : size of RNN hidden cell
--cell_type         : specify RNN type

Testing

To evaluate the run:

python test.py [--args=value]

Hyperparamters

// hyperparamters for model learning
--max_epochs        : 20
--batch_size        : 64
--lr_rate           : 0.005
--clip              : 5.0
--l2_norm           : 0.00001
--dropout           : 0.0
--optim             : Adam

// network structure
--emb_size          : 50
--use_attn          : True
--hid_size_enc      : 150
--hid_size_pol      : 150
--hid_size_dec      : 150
--cell_type         : gru

multiwoz-mdrg's People

Contributors

budzianowski avatar jiahuan-pei avatar

Stargazers

 avatar  avatar

Watchers

 avatar  avatar  avatar

Forkers

zixufang

multiwoz-mdrg's Issues

data load failed

It turns out " FileNotFoundError: [Errno 2] No such file or directory: 'data/multi-woz/mapping.pair' " when I running " python multiwoz/Create_delex_data.py " first time.

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.