Home

Awesome

Language Emergence

Code for the paper

Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog
Satwik Kottur, José M. F. Moura, Stefan Lee, Dhruv Batra
Arxiv

This repository contains code to train, evaluate, and visualize dialogs between conversational agents (Abot and QBot) that talk about instances in an abstract world.

If you find this code useful, consider citing our work (ACL Anthology):

@inproceedings{kottur-etal-2017-natural,
    title = "Natural Language Does Not Emerge {`}Naturally{'} in Multi-Agent Dialog",
    author = "Kottur, Satwik  and
      Moura, Jos{\'e}  and
      Lee, Stefan  and
      Batra, Dhruv",
    booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
    month = Sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/D17-1321",
    doi = "10.18653/v1/D17-1321",
    pages = "2962--2967",
}

Setup

All our code is implemented in PyTorch. Current version has been tested in Python 3.6 and PyTorch 1.4.

Additionally, our code also uses some famous python packages that can be installed as follows:

pip install json
pip install tqdm
pip install pickle
pip install json

Contents

Usage

Checkout run_me.sh to see how train our model.

Pretrained models and detailed documentation coming soon!

Contributors

License

BSD-3