My research interests focus mainly upon natural language processing, and Artificial Intelligence in general. At some point I decided that writing computer programs was not going to teach us anything about natural intelligence, so I view the study of AI as an attempt to model those processes that are traditionally thought to require intelligence, rather than an attempt to create genuine intelligence on a machine.
My current areas of interest are:
Articles from journal papers are often reported in popular science periodicals or national newspapers. However, a New Scientist article often has very different linguistic properties to the original article that it is reporting on. Length, structure, and especially vocabulary are different in both cases, reflecting the documents' different target audiences. I am interested in how to align the content of documents which are on the same subject, but are taken from such different genres. Being able to align an article written for a general audience with one written for a specialised audience should improve the access to information in digital libraries for interested, but non-specialist, audiences.
- how (same language) texts can be aligned across genres,
- how (computational) natural language applications can interact with other domain-specific resources,
- how technical terminology is used in natural language resources; how to extract technical terms and how to recognise when synonyms or paraphrases are being used.