Building Journalistic Knowledge Graphs for Exploratory Text Analysis (iCASE - BBC)
The interpretation of complex and large-scale textual data is an intrinsic part of the journalistic activity. Understanding multiple perspectives involved in a political debate, monitoring the evolution of the public discourse around a specific issue or collecting factual evidence, are examples of complex interpretation tasks which currently require great manual effort.
The recent evolution of Natural Language Processing (NLP) techniques brings the opportunity to automatically structure, integrate, classify and cluster textual content at scale, facilitating the analysis of complex domains of discourse. NLP can provide the fundamental infrastructure to dramatically reduce the barriers for more comprehensive, deeper and unbiased journalistic analysis.
This project is a partnership between the School of Computer Science at the University of Manchester and the BBC and it focuses on the coordination of multiple text classification and information extraction techniques for the construction of knowledge graphs which can support journalists in complex analytical tasks. The PhD student will work at the interface between NLP and Knowledge Representation, proposing and evaluating inter and intra-sentence meaning representations models to address demands of journalists in the real-world. The project will explore the application of multiple state-of-the-art machine learning techniques for discourse analysis such as story/narrative extraction, argumentation mining, opinion mining.
The Supervision Team and Study Environment
The selected candidate will be co-supervised by the BBC R&D Labs in London. The British Broadcasting Corporation (BBC) is a British public service broadcaster. It is the world’s oldest national broadcasting organisation and the largest broadcaster in the world by number of employees. The BBC R&D Labs are the research arm of the BBC providing the supporting innovations though the BBC production and broadcasting chain.
The University of Manchester boasts one of the most innovative and successful schools of computer science in the world. Manchester saw the birth of computer science, with the creation of the world’s first stored-program computer. We continue to work on pioneering research with widespread activity and strength in a range of key aspects of computer science from hardware through to user interaction.
The School of Computer Science was ranked in the top 5% in the UK (4th out of 89 submissions) based on GPA for Computer Science and Informatics in REF2014, the most recent UK research assessment. REF2014 also assessed that The University of Manchester is the best environment in the UK for computer science and informatics research, with 94% of our research being classed as "world-leading" (4*) or "internationally excellent" (3*). All our "impact" case studies were ranked 3* and 4*, which puts us joint-top for research impact.
Applicants should have or expect to obtain a BSc 1st Class or MSc with Distinction in computer science or a related discipline and should have strong programming skills. Experience in Natural Language Processing and Machine Learning projects are highly desired. Applicants must also have British citizenship or be a permanent resident and have lived in the UK for the last 3 years. Exceptional EU students may be eligible.
Academic Supervisor: Andre Freitas (UoM, School of Computer Science)
Industrial Supervisor: Chris Newell & Andrew McParland (BBC R&D Labs)
Qualified applicants are strongly encouraged to informally contact Andre Freitas (email@example.com) or Chris Newell (firstname.lastname@example.org) to discuss the application prior to applying.
Please submit a full application via the standard application route.
Applications are invited for this fully funded (tuition fees plus additional stipend), full-time PhD EPSRC iCASE studentship, to start in September 2019 or as soon as appropriate. It is intended that this studentship is part of a newly established partnership between the University of Manchester and the BBC R&D Labs.