Dialog/Action Skill Analysis for Watson Assistant

Introduction

Dialog/Action Skill Analysis is a Python framework along with an easy-to-use Python notebook to help you quickly and effectively build AI assistants using Watson Assistant

Whether you are new to the process and are building your first AI assistant or you’re a veteran and have an assistant working well in production, this framework is intended to help everyone with questions like...

• How do I know my assistant is doing a good job?
• How do I test and measure my assistant’s performance?
• Why is the assistant responding incorrectly to this question?
• How do I improve my assistant’s ability to understand questions?

Currently Supported Languages: en, fr, cs, de, es, it, pt, nl, zh-cn, zh-tw

Usage

If you clone the notebook from this repository locally, please use the steps below. For usage in Watson studio, please refer to the section below on Hosted Python Notebook

1. Assumes familiarity using a Python Jupyter notebook
2. Assumes a Python 3.9 or greater environment (We recommend using Anaconda to setup a python environment)
3. Install dependencies with pip install -r requirements.txt
4. Start jupyter server with jupyter notebook
5. Run classic_dialog_skill_analysis.ipynb or new_experience_skill_analysis.ipynb to start session

Update: March 15th 2023

new_experience_skill_analysis.ipynb for dialog or action analysis under new Watson Assistant experience is available.

Guides

An introduction to Dialog Skill Analysis on Medium: Announcing Dialog Skill Analysis

Hosted Python Notebook

For those of you familiar with IBM Watson Studio, we have also made a hosted version of the notebook available on the IBM Gallery: Hosted Dialog Skill Analysis Notebook

Current Contributor List

Haode Qi	Cheng Qian	Ladislav Kunc

Previous Contributor List

Panos Karagiannis	Ming Tan
Navneet Rao	Yang Yu