Skip to main content

Dealing with publication information overload

Primary supervisor

Wray Buntine


Information overload is now the normal state of affairs for knowledge workers.  In keys areas such as COVID-19 research or Machine Learning, the volume of new content is growing seemingly exponentially in recent years.  We need to apply recent developments in natural language processing, information retrieval and machine learning to address the problem of information overload by, for instance, developing and integrating advanced search, community detection and summarisation techniques to work on our own literature, or on content such as PubMed or arXiv.    For instance, Alibaba's iDST (Institute of Data Science of Technologies) won a recent deep learning passage retrieval competition at TREC 2019 by a clever combination of deep NLP and IR.

Required knowledge

Practical knowledge of using modern deep learning methods as well as extensive experience with Python programming.

Standard Machine Learning, Artificial Intelligence and Natural Language Processing as covered in masters or advanced undergraduate subjects.

Good understanding of Machine Learning principles.

Learn more about minimum entry requirements.