School of Computing Science - Learning to Ask for Effective Conversational Search
The University of Glasgow (UofG) is home to world-leading research in the fields of information retrieval (search) and machine learning. This PhD project is funded by a Google Faculty Award and will be co-supervised by Filip Radlinki of Google Research AI in London.
We are searching for a highly motivated student to work at the interface between search, machine learning, and natural language processing.
The aim of this PhD is to research Conversational Artificial Intelligent (AI) systems that focus on Conversational Information Seeking. The goal is to create proactive search agent systems that “learn to ask” the right questions from the user at the right time to effectively direct an information conversation and accomplish their tasks efficiently. It will study state-of-the-art task-based agent systems, including those based on deep learning models and that utilize reinforcement (and transfer) learning to learn agent policies. The research will also cover knowledge representation and research on construction of subjective personal knowledge graphs from conversation.
Despite recent advances in conversational artificial intelligence systems, such as the Google Assistant, today’s virtual assistants are capable of limited “conversations”, with many consisting of a single turn. In the future information assistants will be able to help users with task-oriented information exchanges on complex topics. This research area, Conversational Information Seeking (CIS), is highlighted as a key emerging area in search by the recent Strategic Workshop on IR (SWIRL) 2018 report. Example CIS topics include information tasks such as “teach me about the causes of climate change” or “talk to me about Mozart versus Beethoven.” For a related conversational benchmark, see the TREC Conversational Assistant Track (CAsT) (http://treccast.ai).
“Learning to ask” effective questions in mixed-initiative information seeking conversations is a core building block of effective conversational search systems. This PhD will provide new insights into types of interactive feedback and the conditions under which different types of feedback are effective. It will result in the development of new conversational feedback models.
The ideal candidate will have:
● A strong first degree in Computer Science or related discipline
● An interest in conversational artificial intelligence -- including deep learning methods and reinforcement learning, information retrieval, and natural language understanding.
● An understanding of research principles and methods, through an undergraduate or postgraduate dissertation project.
Applications will be considered on a rolling basis. For enquiries specific to the project, please contact: [Email Address Removed]
Start Date: October 2019
How to Apply: Please refer to the following website for details on how to apply:
Funding is available to cover tuition fees for UK/EU applicant for 3.5 years, as well as paying a stipend at the Research Council rate (estimated £15,099 for Session 2019-20).
How good is research at University of Glasgow in Computer Science and Informatics?
FTE Category A staff submitted: 41.60
Research output data provided by the Research Excellence Framework (REF)
Click here to see the results for all UK universities