We are seeking to appoint two fully funded PhD students in Computer Science in collaboration with Rolls Royce Ltd.
Closing application date: Friday 15th July 2022.
Starting date: 1st October 2022.
The successful candidates will work on two projects entitled “Extracting subject-specific knowledge graphs from natural language” and “Guiding engineering design by text corpora and knowledge graphs”.
The projects are focused on developing methods for extracting and applying technical and regulatory information from text to support engineering and other application areas.
What is offered
The studentship consists of a full fee waiver (national or international) and a stipend of £16,000 per year, for three years (subject to funding confirmation).
The studentships will be awarded based on academic achievement and the potential to produce cutting edge research. Prospective applicants must:
- Hold a good Master’s degree (no less than a second class honours degree or an equivalent qualification) in Computer Science, Artificial Intelligence or related fields. We will also consider applications from those with a good honours degree or extensive professional experience in the area;
- Proficiency in two or more of the the following areas:
- implementation and evaluation of deep learning architectures and algorithms;
- natural language processing methods and models;
- knowledge graphs in theory and practice;
- integration of neural networks with symbolic knowledge and reasoning;
- Proficiency in programming in Python;
- Be able to demonstrate proficiency in the use of oral and written English.
How to Apply
You are strongly encouraged to discuss your application in advance with Dr Tillman Weyde.
Visit our Computer Science research degrees web page for further information on making a formal application. When submitting your proposal, enter the title “Rolls Royce Collaboration” and you will automatically be considered for this studentship.
The online application can be found in the ‘How to apply section’ in the web link above and should include the following supporting documents:
- Copies of Degree Certificates and Transcripts in official English translation - original will be requested before an offer is made.
- Official work e-mail addresses (not private ones) for two referees (one of which must be an academic).
- Proof of English Language proficiency (minimum average score of 6.5 IELTS, with a minimum of 6.0 in each of the four components) if English is not your first language.
- Passport copy.
Extracting subject-specific knowledge graphs from natural language text for design and regulations
This project is about designing, developing, and evaluating methods for the extraction of information from text. The methods will be developed initially for aerospace engineering, but will also be applicable to other domains and may be evaluated on other domains. The nature of the knowledge to be extracted can range from physical relationships, over empirical insights, to regulations on safety and other aspects.
It will be extracted and stored in knowledge graphs and pre-existing knowledge will have to be taken into account. The methods will be based on current approaches using large pre-trained languages models as well as novel methods for knowledge integration. The evaluation will be conducted in the R2 Factory environment.
Guiding engineering design by text corpora and knowledge graphs
This project is about applying knowledge, pre-formalised in graphs or extracted text corpora, to support and validated design processes. The process of design, be it for engineering, software, or business process, is complex and can often benefit from guidance based on knowledge. This applies to underlying principles and empirical data, as well as regulation, that needs to be followed to ensure that the design meets all requirements.
There are several challenges in this context, including that are most background knowledge and especially regulation is often given in text, while many design outputs are of different modalities, such as drawings, 3D models, mathematical formulae or software code. Designing models that apply knowledge from text to design artefacts and methods to integrate these models into the design process will be developed and evaluated in the in the R2 Factory environment.