PhD Studentship - Building Trustworthy Conversational Search Agents

Conversational agents are allowing people to communicate with computers in a natural way.  A new generation of conversational search agents has arisen with increased proliferation of voice-based search via personal assistants (Alexa, Siri, Cortana, and many others). Such agents allow people to ask questions regarding their information needs. Currently, such systems handle simple questions-and-answers (what is the weather like, etc.), but now with the rise of deep learning it is possible to have a conversation with the agents -- where people can ask about and learn about a particular topic over a series of interactions. While such agents are growing in popularity and use, there are many open research challenges regarding their design, development and evaluation. One such issue is Trust!
Imagine talking to your favourite agent, and asking it for recommendations on where to dine out in the city you are visiting. Do you take the first suggestion? Or do you explore a number of options? Or do  you trust the agent to give you good suggestions? Maybe they are hiding something from you? Or maybe they get a commission on their recommendations?
Thus, the topic of this PhD is focused on evaluating conversational search agents with respect to their usability, effectiveness, and trust. Specifically investigating what biases might arise due to interactions with conversational agents -- to determine how much influence an agent might assert over a user.
There are many open challenges across diverse areas: building conversational agents, modelling the interactive search process, explainable and transparent agents, measuring trust and bias in conversational search, etc. The target research area will depend on the candidate's experience and interests. However, the successful candidate will be expected to design, develop, and evaluate conversational search agents.
Eligibility criteria
The studentship is open to UK and eligible EU citizens (with settlement status) with a background in Computer Science/Information Science or related fields.
Candidates for a PhD Studentship should demonstrate outstanding qualities and be motivated to complete a PhD in 3 years and must demonstrate:

  *   Outstanding academic potential as measured normally by either a 1st class honours degree (or equivalent Grade Point Average (GPA) or a Master's degree with distinction or equivalent).
  *   An IELTS (Academic) score of 6.5 minimum (with a minimum 6.0 in each component, or equivalent) for candidates for whom English is not their first language and this must be evidenced at point of application.


Candidates will ideally:

  *   Have experience of Machine Learning, Natural Language Processing OR Information Retrieval
  *   Have experience in Human Computer Interaction
  *   Strong programming skills (in Python)


In addition to satisfying minimum entry criteria, the advisory team will look closely at the qualities, skills and background of each candidate and what they can bring to their chosen research project in order to ensure successful completion.
Applicants should submit a CV and a proposal (approximately 1500 words) outlining their understanding of the area, the approach they would envisage taking and what qualities they will bring to the research community. This project will be supervised by Dr Martin Halvey and Dr Leif Azzopardi. Applications should be submitted to Dr Martin Halvey ([email protected]<mailto:[email protected]>)
What does the funded studentship include?
Funded candidates will receive a maintenance grant of approximately £16,000 per annum to cover their living expenses, with an annual cost of living increase. Fees for UK or eligible EU citizens (with Settled Status) will also be covered.
Closing date: The first call for applications will close on 15th of May, 2022.

Dr Martin Halvey
----------------------------------------------------
Reader (Associate Professor) in Multimodal Interaction
Director Postgraduate Teaching
Course Director MSc Information Management
Department of Computer and Information Sciences
University of Strathclyde
----------------------------------------------------
[email protected]<mailto:[email protected]>
0141 553 6027




########################################################################

To unsubscribe from the IR list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=IR&A=1

This message was issued to members of www.jiscmail.ac.uk/IR, a mailing list hosted by www.jiscmail.ac.uk, terms & conditions are available at https://www.jiscmail.ac.uk/policyandsecurity/