Knowledge Graph Construction via Learning and Reasoning

Project description

Knowledge graphs (KGs) are graph-structured knowledge resources which are often expressed as triples such as ("UK", "hasCapital", "London") and ("London", "instanceOf", "City"). As well as such basic "facts", KGs often include structural knowledge about the domain or of experts, typically based on a hierarchy of entity types (a.k.a. classes or concepts), e.g., ("City", "subClassOf", "HumanSettlement"), and logics in the form of rules and ontological axioms. KGs also include ontologies which are often used by domains for representing human knowledge with reasoning supported, e.g., the SNOMED ontology in clinic settings. All these KGs have been widely used as the backend of AI and information systems, such as in Google search engine, Alexa and Siri.

The Information Management Group at the University of Manchester invites applications for PhD candidates in the area of KG construction. PhD projects in this area will explore how contemporary techniques in Machine Learning (such as Transformer and Semantic Embeddings), Knowledge Engineering (such as Knowledge Representation and Reasoning) and Data Engineering can be used as a foundation to KG construction and curation.

Examples of research challenges include: 1) how to extract new knowledge from tables and text; 2) how to insert the new knowledge into a KG; 3) how to integrate different KGs with matching; 4) how to curate KG, e.g., completion, with symbolic reasoning and machine learning prediction.

Applicants are expected to have:

1. An excellent undergraduate degree in Computer Science or Mathematics (or related discipline), and preferably, a relevant M.Sc. degree.
2. Confidence and independence in programming complex systems in Java or Python.
3. Previous academic or industry experience in at least one of the relevant topics such as Machine Learning, Natural Language Processing, Semantic Web, Knowledge Engineering, Data Engineering and Data Science.
4. Excellent report writing and presentation skills.

Please note that applicants must additionally satisfy the standard requirements for postgraduate studies at the University of Manchester, such as a first-class or high upper-second class (or an equivalent international qualification) and English language qualifications, as stated in the PGR guidelines.

Qualified applicants are strongly encouraged to informally contact Jiaoyan Chen (jiaoyan.chen@manchester.ac.uk) and Norman Paton (norman.paton@manchester.ac.uk) to discuss the application prior to applying.