Artificial Intelligence Methods for Conversational Agents in Healthcare

Facilitators:

Will Kearns, Aakash Sur, BHI PhD Students and Trevor Cohen, BHI Faculty

Details:

Tuesdays, Autumn Quarter: 11:30 am-12:20 pm, Health Sciences Building, T478

Course Description:

Through this course, students will be introduced to reinforcement learning methods and how to apply them to train health dialog systems to address specific problems in healthcare. We will cover a range of machine learning methods including tree search, tree pruning, Markov decision processes, and Q-learning. We will explore both classical methods and recent advances in the development of dialog system components including natural language understanding, dialog management, and natural language generation. The course structure will be a mixture of lectures and interactive coding sessions culminating in the deployment of a health dialog system.

We welcome questions during the class as others might share the same questions. If you need individual help, please see one of the instructors after class or send a question to the group on slack.

Course Reading:

Neural Approaches to Conversational AI Question Answering, Task-Oriented Dialogues and Social Chatbots

Designing Voice User Interfaces: Principles of Conversational Experiences

Week 1 - 10/1/19

Title:

Introduction to Conversational Agents and Reinforcement Learning

Description:

We will introduce conversational agents operating within a natural language environment, an ideal context for employing reinforcement learning (RL). We will survey the methods of RL and its applications of NLP. Finally, we will cover the software requirements for the class, and ensure students can interactively follow along in coding exercises.

Lecture:

Week 1 Slides

Reading:

Write an NLU model

Coding:

None

Week 2 - 10/8/19

Title:

Natural Language Understanding

Description:

We will explore how we can train agents to understand their conversational environments.

Lecture:

Week 2 Slides

Reading:

ONENET:Joint Domain, Intent, Slot Prediction for Spoken Language Understanding

Dynamic Integration of Background Knowledge in Neural NLU Systems

Coding:

Train NLU model: with a Pipeline in Rasa

Week 3 - 10/15/19

Title:

Tree Search

Description:

We will model decisions as trees and learn to efficiently search them using classic algorithms such as breadth-first search and depth-first search. In addition, we will introduce heuristic based searches, including A* search.

Lecture:

Week 3 Slides

Reading:

Joint A* CCG Parsing and Semantic Role Labelling

Coding:

Week 3 Coding

Week 4 - 10/22/19

Title:

Advanced Tree Searches

Description:

We will cover how to model two player games as trees, and how the optimal strategy can be recovered from these trees. In addition, we will cover how to prune these trees to limit the total search space using alpha-beta pruning, and heuristic pruning.

Lecture:

Week 4 Slides

Reading:

None

Coding:

In Class Exercise with Grundy’s Game of Nim

Week 5 - 10/29/19

Title:

Dialog Management

Description:

Reading:

Health dialog systems for patients and consumers

An overview of end-to-end language understanding and dialog management for personal digital assistants

Coding:

Train Rasa DM with Interactive Learning

Week 6 - 11/5/2019

Title:

Markov Decision Processes

Description:

In this class, we will extend our tree based decision models to graphs with Markov models. We will learn how to calculate the best route through a Markov decision process (MDPs) using the Bellman equations. Finally, we will extend these ideas to conversational agents using partially observable Markov decision processes (POMDPs).

Lecture:

Week 6

Reading:

POMDP-Based StatisticalSpoken Dialog Systems:A Review

Training a real-world POMDP-based Dialogue System

Coding:

None

Week 7 - 11/12/2019

Title:

Q-Learning

Description:

Here we will introduce one of the key concepts in RL, Q-learning. This approach overcomes the limitations of MDPs and allows us to conduct on-line or off-line learning without complete information.

Lecture:

Week 7

Reading:

TBD

Coding:

TBD

Week 8 - 11/19/2019

Title:

Deep Q-Networks

Description:

Moving past basic tabular Q-learning, we will cover current approaches which revolve around Deep Q-Networks (DQN). We will cover popular examples of DQNs used to master video games, and conversations. Finally, we will cover how to efficiently train these models using experience replay.

Lecture:

Week 8

Reading:

Playing Atari with Deep Reinforcement Learning

Agenda-based user simulation for bootstrapping a POMDP dialogue system

A User Simulator for Task-Completion Dialogues

Coding:

Week 8: Deep Learning

Week 8: Cart Pole

Train dialog policy w/ episodic replay

Train a DQN using an agenda based User Simulator

Week 9 - 11/26/2019

Title:

Advanced Neural Methods for Dialog Systems

Description:

We will cover advanced neural architectures for training dialog systems, e.g. A2C and MemNN models.

Reading:

ConveRT: Efficient and Accurate Conversational Representations from Transformers

The Illustrated Transformer (Transformer Tutorial)

Coding:

TBD

Week 10 - 12/3/2019

Title:

Ethics and NLG

Description:

We will finish off the course with a discussion of ethics in the development of dialog systems using two case studies and then focus the discussion on health dialog systems in particular.

Reading:

The Design and Implementation of XiaoIce, an Empathetic Social Chatbot

Twitter taught Microsoft’s AI chatbot to be a racist asshole in less than a day

Coding:

TBD

Recent Posts