Codebase for Zero-Shot Dialog Generation with Cross-Domain Latent Actions, published as a long paper in SIGDIAL 2018. Reference information is in the end of this page. Presentation slides can be found here.
This work won the best paper award at SIGDIAL 2018.
If you use any source codes or datasets included in this toolkit in your work, please cite the following paper. The bibtex are listed below:
@article{zhao2018zero,
title={Zero-Shot Dialog Generation with Cross-Domain Latent Actions},
author={Zhao, Tiancheng and Eskenazi, Maxine},
journal={arXiv preprint arXiv:1805.04803},
year={2018}
}
python 2.7
pytorch >= 0.3.0.post4
numpy
nltk
The data folder contains three datasets:
The following scripts implement 4 different models, including:
Run the following to experiment on the SimDial dataset
python simdial-zsdg.py
Run the following to experiment on the Stanford Multi-Domain Dataset
python stanford-zsdg.py
The hyperparameters are exactly the same for the above two scripts. To train different models, use the following configurations. The following examples are for simdial-zsdg.py, which also apply to stanford-zsdg.py.
For baseline model with attetnion decoder:
python simdial-zsdg.py --action_match False --use_ptr False
For baseline model with pointer-sentinel mixture decoder:
python simdial-zsdg.py --action_match False --use_ptr True
For action matching model with attetnion decoder:
python simdial-zsdg.py --action_match True --use_ptr False
For action matching model with attetnion decoder:
python simdial-zsdg.py --action_match True --use_ptr True
The following are some of key hyperparameters:
All trained models and log files are saved to the log folder. To run a existing model, you can: