Crowdsourced conversational avatar framework

  • Crowdsourced conversational avatar framework
EEECS Summer Research Internships 2018

Proposed Project Title:

  • Crowdsourced conversational avatar framework

Principal Supervisor(s):
  • John Bustard


Project Description:

Existing commercial conversational agents are primarily the result of many manually constructed conversation trees.

The goal of this project is to combine recent machine learning based chat bot AI[1] with a more traditional tree based conversation system. The objective is that users can review possible responses from the AI and suggest new statements so that through many users interacting with the system more interesting and inteligent conversations can take place.


Objectives:

Create a hybrid chatbot AI system that provides suggestion conversation statements (like a computer game) and can respond to free form statements (like a chat bot).

The system should combine a deep learning based system for suggesting replies with a dialog graph. The system enables users to improve the system by rating and suggesting alternative statements at each stage, creating a framework for crowdsourcing interesting chatbot conversations.

The system will require a means to enable users to assess other users suggestions for moderation purposes and so the system can weight or excluded feedback from different users.


Academic Requirements:

The scheme is open to all EEECS Undergraduates (apart from students on the BIT degree pathway and students who are due to graduate this summer)

This project can be developed in Java and is suitable for a student who is a capable programmer and has an interest in exploring different ways of formalising conversation. The project requires creativity and a skill in formalising and generalising and will provide a very useful preparation for PhD level research thinking.


General Information:

Each internship will last between 6-8 weeks and will pay a weekly stipend of £250.

Accommodation and travel costs are not provided under this scheme.

Start date: (Flexible based on student availability provided the project is complete before the start of term)

Duration:  8 (Weeks)

Location: Computer Science Building (IoT Lab)

Further information available at: http://www.qub.ac.uk/schools/eeecs/Research/


Contact details:

Supervisor Name: John Bustard
Address:

Queens University of Belfast
School of EEECS,
Computer Science Building,
18 Malone Road,
Belfast
BT9 5BN

Email: j.bustard@qub.ac.uk