Skip to main content

PhD Studentship - Generation of Conversational Databases

  • Delivery:
    Full time according to Funding Council definitions

PhD studentship - Efficient Generation of Conversational Databases – Conversational AI Technologies for Digital Characters

This project will be part of BU Doctoral Training Centre - Centre for Digital Entertainment (CDE).

The Intelligent Virtual Personal Assistant consists of three landmark components that enable Intel-PA to perform human-like communications with real humans. These are:

  • Sensible conversations
  • Appropriate body gestures
  • Facial expressions; and the ability to detect the motion and emotions of the human user.

By performing such human-like functions, Intel-PA will be able to play a huge role in assisting mankind in countless applications, such as healthcare, training, education, marketing and decision making, to name but a few.

Working as a multidisciplinary team of researchers and supervisors, we will demonstrate the research by developing an Intelligent Neur-Assistant, an AI-powered conversational animated avatar that can have a plausible initial consultation with a patient with neurological conditions by integrating these six projects.

All students will have to contribute to the overall objectives of the research with each of them concentrating on an individual research project.

Find out more about the Centre for Digital Entertainment.

This is a fully-funded PhD studentship which includes a stipend of £15,450 each year to support your living costs.

This project is conditional upon the funding being secured.

The closing date for applications is 31 October 2021.

Key information

Next start date:

24 January 2022

Location:

Bournemouth University, Talbot Campus

Duration:

4 years

Entry requirements:

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. If English is not your first language you'll need IELTS (Academic) score of 6.5 minimum (with a minimum 6.0 in each component, or equivalent). For more information check out our full entry requirements

Additional criteria:

An applicant is expected to have experience of Machine Learning and Natural Language Processing.

International entry requirements:

Candidates for a PhD Studentship should demonstrate outstanding qualities and be motivated to complete a PhD in 4 years and must demonstrate:

  • 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.

Project details

This project will be part of BU Doctoral Training Centre - Centre for Digital Entertainment (CDE).

AI and machine learning has been used for natural language understanding and generation for many years, which has reshaped the technology landscape. Continuous meaningful conversation generation brings huge challenges, which requires understanding the dynamic context to keep the conversation flowing. In the long-term, AI-driven devices with sophisticated network structures and sensors will grow continuous learning ability to make such devices versatile and adoptive for natural conversations.

There are many challenging tasks to generate sensible dialogs to support interaction among virtual agents or between an agent and a human user. The proposed research is about the development of novel technologies for maintaining and evolving a dynamic conversation database to assist the development of conversational AI. The dialog context, including the back and forth dialogs, is preserved in the database for further analysis. The database will help automatically (or semi-automatically) train and drive the conversational AI conversations. Based on a given scenario and common senses, the agents can retrieve dialog information from the database, search for content in the knowledge base system, or generate new conversation threads dynamically, leading to natural conversations. 

The key is to effectively generate the conversational databases which support human-like conversations to process and understand multiple intents within one query, including features such as multiple intents per entity and nested intents. A machine learning framework will be developed to offer end-to-end language transforming and attention mechanisms when generating dialog contents. The databases will provide the virtual agents with the capacity of building up understanding, making corrections and updating the context while dialogues continue.

Such a database will support the interpretation and understanding of emotions, allowing creating dialogs that can read and respond naturally during a conversation.

Find out more about the Centre for Digital Entertainment.

View the full product description (pdf 204kb)

The closing date for applications is 31 October 2021.

Supervisors

Professor Jian Chang

Professor Jian Chang is an active scientist in computer animation with over 15 years’ research experience in a world-leading centre, the NCCA, the UK No.1 educational and research base for computer animation. His research has focused on physics-based modelling (deformation & fluid), motion synthesis, virtual reality (surgery simulation), and novel HCI (eye-tracking, gesture control and haptic). He is keen to exploit the usage of novel computer animation techniques for cross-disciplinary research and applications, which has led to international research collaboration and joint funding bids. His research has been funded by various funding sources, including the Royal Society, EU FP7, InterReg VA France (Channel) England, and HEIF. 

Please contact Professor Jian Chang for informal enquiries: jchang@bournemouth.ac.uk 

Funding

A fully-funded Studentship includes a maintenance grant of £15,450 per year to contribute towards living expenses during the course of your research, as well as a fee waiver for 48 months.

Associated costs, such as for fieldwork and conference attendance, will also be met under the Studentship.

Academic support

The Research Development Programme, developed by the Doctoral College in line with the Researcher Development Framework (Vitae).

An added benefit is the opportunity to meet researchers from other academic schools at BU through the activities of the Doctoral College and benefit from their experiences, skills, and perspectives.

Full entry requirements

The BU PhD and MRes Studentships are open to UK, EU and International students.

Candidates for a PhD Studentship should demonstrate outstanding qualities and be motivated to complete a PhD in 4 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.

In addition to satisfying minimum entry criteria, BU 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 will be asked to submit an online application form and a proposal (approximately 1500 words) outlining their understanding of the project for which they are applying, the approach they would envisage taking and what qualities they will bring to the research community.

Please note:

  • current BU Doctoral students are not eligible to apply for a Studentship
  • current MRes/MPhil students can apply, subject to satisfactory completion of their Research Degree prior to being able to take up the award
  • PhD Studentships cannot be used to support BU staff to complete doctoral programmes.

Additional Eligibility Criteria: 

  • The applicant should have experience of Computer Science, Machine Learning System and Natural Language Processing. 

International entry requirements

If English is not your first language, you will need to provide evidence that you can understand English to a satisfactory level. English language requirements for this course are normally: 

IELTS (Academic) score of 6.5 (with a minimum 6.0 in each component) or equivalent.

View further information about our English language requirements.

A number of pre-sessional English and preparatory programmes are offered through our partner institution, Bournemouth University International College, and will get you ready for study at BU at the appropriate level.

You can also find further details of the international qualifications we accept, and what level of study they apply to, on our postgraduate entry requirements page.

How to apply

Click the green ‘Apply now’ button at the top of the page and complete the online application form. You can find further guidance about applying for a postgraduate research degree in our Postgraduate Research section.

The closing date for applications is 31/10/2021.

Careers

A research degree can open new career opportunities in commercial research and development, consultancy, or could lead you to starting your own business. You may alternatively consider a career in academia. You may wish to undertake research to contribute to your knowledge of a specialist subject, or develop your employability by enhancing your skills in project management and analysis.

hummingbird

The Doctoral College

See how we work alongside Academic Schools and the Faculty to support the postgraduate community at BU.

Science forensic toxicology research

Fees and funding

Find out about the fees and different funding options for postgraduate research degrees.

Statistics shown throughout this page are taken from Unistats and BU institutional data unless otherwise stated.