Skip to content

Implementation of Supervised embedding models from [Learning End-to-End Goal-Oriented Dialog] paper.

License

Notifications You must be signed in to change notification settings

sld/supervised-embedding-model

Repository files navigation

Description

It is the implementation of Supervised embedding models from [Learning End-to-End Goal-Oriented Dialog] paper.

Results almost the same as in the paper.

Here you can find Russian paper-note of the paper: link.

Environment

  • Python 3.6.0
  • tensorflow 1.0.0
  • Dialog bAbI Tasks Data 1-6 corpus, download by the link. This corpus should be placed in data/dialog-bAbI-tasks directory.

All packages are listed in requirements.txt.

Reproduce results

  1. Setup the environment.
  2. Run: bin/train_all.sh
  3. After approx. 1 hour run it in test set: bin/test_all.sh

Results

16.03.17.

In the table per-response accuracy is shown.

Task Supervised Embedding (Article) Supervised Embedding (Ours)
T1: Issuing API calls 100 99.6
T2: Updating API calls 68.4 68.4
T3: Displaying options 64.9 56.9
T4: Providing information 57.2 57.1
T5: Full dialogs 75.4 62.1
T6: Dialog state tracking 2 22.6 10.8

Open question:

  1. When we training with use_history=True should we test on pre-processed dataset as in train? Or should we concat each output in test and build history on the fly?

About

Implementation of Supervised embedding models from [Learning End-to-End Goal-Oriented Dialog] paper.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published