queenley / pedp

“Think Before You Speak”: Improving Multi-action Dialog Policy by Planning Single-Action Dialogs (IJCAI-22 long oral presentation)

PEDP

“Think Before You Speak”: Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs IJCAI-22 long oral presentation

This is the codebase for the proposed multi-action dialog policy model PEDP and all the SL-based baseline models (gCAS, DiaMultiClass, DiaMultiDense, and DiaSeq).

For other models, we refer readers to the official implementations. (GDPL and DiaAdv)

---

Requirements

Please refer to environment.yml and prepare the environment with Anaconda.

---

Data

We report results on:

1. MultiWOZ. Please download the data from here and unzip under ./data directory.

2. SGD. Please download the data from here and unzip under ./sgd_data directory.

---

Run

To reproduce the results on MultiWOZ, execute:

python -u main.py --pedp --residual

To reproduce the results on SGD, execute:

python -u main.py --pedp --residual --sgd

To train other models, execute:

python -u main.py --[model_name]

More hyper-parameters are assigned in args.py and can be modified using --para=value.

Dataset schema is defined in config_multiwoz.py and ./sgd_data/config.py for MultiWOZ and SGD, respectively.

---

Results

You can use tensorboard to check the results. Execute:

tensorboard --bind_all --logdir=./log/tb/[file name]

and open the corresponding website.