Processing Natural Language Text into High Quality RDF Graphs
We find an abundance of information on the internet that is presented in natural language, e.g. written English. Such information is ”unstructured’’ in the sense that it is not machine-readable, thus making it infeasible to formally or automatically analyse for the purposes of information extraction, querying, linking, or repurposing. Making natural language machine readable would enable development of many different applications with significant impact such as question-answering on the internet, interactive dialogue systems, reasoning tools using natural language, text summarisation, and others. There have been advances the last several years, resulting in improved tools that parse and semantically represent text, then process it into a machine-readable format, e.g. RDF, that is highly suited to extraction, querying, linking, and so on. Thus, there exists a processing “pipeline’’ to take natural language into machine-readable formats. While the pipeline functions, it is very limited.
The objective of this PhD project is to extend the capabilities of current tools to additional syntactic and semantic constructions, train the tools on alternative corpora (health, law, environment), to improve RDF output with auxiliary information from ontologies or structured knowledge, and to develop a framework to evaluate the performance of the tool.
The outcome of the project will be evaluated in terms of both performance and quality with comparisons to state-of-the-art systems.
During the project, student will also be supervised on the methodology of scientific research, experimenting, writing, presenting, team-working.
The successful applicant should have, or expect to have, an Honours Degree at 2.1 or above (or equivalent) in Computer Science. It is essential for student to have solid knowledge about one of the following disciplines of modern computer science and artificial intelligence: discrete mathematics, knowledge-based systems, machine learning. It is important for the student to have basic understanding of modern database systems and distributed systems. The student should have good programming skills.
There is no funding attached to this project, it is for self-funded students only.
Formal applications can be completed online: http://www.abdn.ac.uk/postgraduate/apply. You should apply for PhD in Computing Science, to ensure that your application is passed to the correct College for processing. Please ensure that you quote the project title and supervisor on the application form.
Informal inquiries can be made to Dr A Wyner, ([email protected]) with a copy of your curriculum vitae and cover letter. All general enquiries should be directed to the Graduate School Admissions Unit ([email protected]).