|
Conversational Agents
Research Centre
|
|
Conversational Agents Research Centre
This centre's mission is to
perform advanced research in the field of Conversational Agents, to
co-operate with international researchers in the field and develop
commercial applications in collaboration with industry.
Conversational agents (CAs) are computer programs which can
participate fully in natural language dialogue with human beings. They
essentially allow communication between a user and a computer using
natural language. There are three key methodologies for developing
conversational agents. The first and more comprehensive is natural
language processing that studies the constructs and meaning of natural
language, applying rules to process information contained within
sentences. The second approach relies on pattern matching of key words and
phrases whilst the third compares the semantic similarity of
phrases to decide what the meaning of the input is (Li, Bandar & McLean
2003), making it more suitable for conversational agents as it will cope
with input which is not grammatically correct or complete.
Current
Projects include
Using conversational agents as natural language interfaces to databases
Development of an adaptive and self aware conversational agent
New methodologies for scripting using sentence similarity measures
Find out more about our University spin off company
Convagent
Ltd
|
