Dialog State Tracking using End-to-End Neural Networks
Switch branches/tags
Nothing to show
Clone or download
Latest commit a102672 Mar 16, 2018

README.markdown

Please contact info@voicy.ai to implement your enterprise needs for Chat Bot/Virtual Agent Technology.

Voicy.AI is pioneering implementation of research papers for Dialog State Tracking and Chat-Bot Technology.

Goal Oriented Dialog System

The objective of this project is to explore neural network architectures for question answering and goal oriented dialog systems. We will train on (6) dialog bAbI tasks. Tensorflow is used for building the models. I have listed some of the influential/interesting papers below. If I have missed something, let me know.

Documentation is available as wiki.

The (6) dialog bAbI tasks

This section presents the set of 6 tasks for testing end-to-end dialog systems in the restaurant domain. Each task tests a unique aspect of dialog.

Setup

# python2 is not supported
sudo -H pip3 install -r requirements.txt
# if this doesn't work, raise an issue

Learning End-to-End Goal-Oriented Dialog

# run main.py without arguments, for usage information
#  usage: main.py [-h] (-i | -t) [--task_id TASK_ID] [--batch_size BATCH_SIZE]
#               [--epochs EPOCHS] [--eval_interval EVAL_INTERVAL]
#               [--log_file LOG_FILE]
#  main.py: error: one of the arguments -i/--infer -t/--train is required
python3 main.py --train --task_id=3 --log_file=log.task3.txt

Results

Task Training Accuracy Validation Accuracy
1 100 99.7
2 100 100
3 100 74.71
4 100 56.67
5 100 98.42
6 76.61 47.08

Hybrid Code Networks

Results

Task Training exmaples Accuracy on Dev set
5 200 100%

Sample Interaction

Papers

Jargons

  • OOV : Out Of Vocabulary
  • hops : number of memory lookups

Credits