PhD studentship - Understanding and Developing Commonsense Reasoning in Conversational AI via Natural Language Processing
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 and 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.
However, most existing conversational AIs only work on context information with pre-defined actions and cannot understand the user intents and reactions. Commonsense reasoning in conversational AI is believed to be the key to solve this problem. Bringing commonsense into Conversational AI understanding, inference and generation is considered to be the next breakthrough in Intelligent Virtual Personal Assistant.
This research project aims to bring an in-depth understanding of commonsense reasoning, investigate how commonsense can help build conversational AI with natural responses to different user’s intent, and model aspects of commonsense inference via NPL and deep learning framework. The project will try to apply commonsense inference for domain applications such as healthcare, education and marketing. The experiment will include creating conversational AI with a range of commonsense knowledge to interact with real humans.
Therefore, this project will pursue three mutually supportive research and development paths: 1) advancing the theoretical frontiers of common sense reasoning in conversational AI; 2) building user satisfaction modules to improve engagement via evaluation; 3) developing and producing practical applications.
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.
Next start date:
24 January 2022
Bournemouth University, Talbot Campus
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.
The applicant should have experience of computer science, machine learning system, 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.