The goal of the project is to equip a robotic companion/dialogue manager with topic modelling and information extraction from corpora, for example Wikipedia articles and topic oriented dialogue corpora, to guide the conversation with a user. Rather than concentrating on a task, a companion engages in free conversation with a user and therefore must supplement traditional rule-based dialogue management with data-driven models. The project thus attempts to examine ways in which text-driven semantic extraction techniques can be integrated with rule-based dialogue management.
Possible directions of this project are:
A. Topic modelling
The system must recognise robustly the topics of user's utterances in order to respond appropriately. This method can be used in addition to a rule-based technique. Given a suitable corpus of topic oriented conversations:
B. Named entity recognition and information extraction for question
The system could take initiative and guide the conversation. It could start with some (Wikipedia) article and identify named entities. If any of the entities match the domain of questions that it can handle, it should generate questions about them.
User: I've been to Paris for holiday.
DM: Paris... I see. Have you been to the Eiffel tower?
C. Question answering
Supervisors: Simon Dobnik and possible others from the Dialogue Technology Lab