Project description

Data Lakes are emerging as data management infrastructures for storing data in various schemata and structural forms. Their goal is to serve as a single entry point for the data analysis process across highly heterogeneous datasets, supporting analytical tasks following a schema-on-read approach, in which data is discovered and integrated when it is to be used. Due to their semantic and structural heterogeneity, Data Lakes bring integration challenges to a new scale of complexity. With the fast development of Artificial Intelligence in recent years, many modern techniques such as Large Language Models and Knowledge Graphs have shown great power in dealing with many problems, including those in data management and data science. These techniques provide a new and promising direction for addressing the challenges in Data Lake.

The Information Management Group at the University of Manchester invites applications for PhD candidates in the area of Artificial Intelligence for Exploration of Data Lakes. PhD projects in this area will explore how contemporary techniques building on Language Models (such as Prompt Learning and Instruction Following Fine-tuning), Knowledge Engineering (such as Knowledge Graphs) and Data Engineering can brought together to explore deep semantics of tabular data for more efficient and effective for Data Lake management.

Examples of research challenges include: 1) how to embed tables in a vector space with their schemas, instances and associated metadata; 2) how to combine semantics from Language Models and Knowledge Graphs for semantic table annotation and schema inference; and 3) how to characterize complex relationships between tables and table attributes and to use these to inform data integration.

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 Postgraduate Research Degree guidelines.