Conversational Response Generation with Linguistic Context and Emotional Context

The objective of this project is to develop methodologies for automatically generating responses in a natural language to converse with humans. Responses directly generated from the question-answer database are inflexible and cannot meet users’ needs. On one hand, the responses should take into account the previous utterances that can keep a conversation more active. On the other hand, the responses should be appropriate for the emotions conveyed in a conversation that can make a conversion more user-friendly. Hence, a more flexible generating system for conversational responses could be created through an artificial intelligence method that is able to incorporate the two types of context information. This research will allow RSVP Technologies Inc., which is currently supporting mostly the tourism market, to expand their dialog system product into a new, broader market.

Faculty Supervisor:

Mark Giesbrecht

Student:

Zhifei Zhang

Partner:

University of Waterloo

Discipline:

Computer science

Sector:

Education

University:

University of Waterloo