Professor Donia Scott: Research ProjectsComputational Linguistics, University of Sussex, UK

*Current & Ongoing Work...*

	Here is a list of some of the projects that I am currently working on or have been involved with in recent times: To view Past Projects, please click here. *CURRENT RESEARCH:* ................................................................................................................................................................................................................................................. Electronic Health Records Natural language and visualisation tools for easy access to large repositories of data-encoded patient records, and for automatically generating a variety of on-the-fly records for individual patients. My work on this topic addresses both primary-care data (the PREP project) and secondary-care data (the CLEF project), supported through funding from the Medical Research Council and the Wellcome Trust. ................................................................................................................................................................................................................................................. Semantic Web Authoring With colleagues at Manchester and the Open University, I am exploring effective methods for opening up the semantic web to a wide range of users, through tools that allow domain experts to define (and view) ontologies and datasets using familiar modes of presentation -- in particular, controlled natural languages. Our intention in the SWAT project is to pursue this objective by applying various technologies from Natural Language Generation. These include knowledge conceptual authoring of the underlying knowledge, and the generation of large organised documents (or hypertexts) to present complex ontologies/data. This work is currently being explored in the SWAT project, with funding from the EPSRC. ................................................................................................................................................................................................................................................. Text Regeneration Automatically generating a range of new versions of a human-generated text. This builds on our theory of Document Structure. ................................................................................................................................................................................................................................................. Natural Language for Biomedicine The development of generic methods and tools supporting critical tasks in medical and biomedical informatics. This is an EU Network of Excellence entitled Semantic Interoperability and Data Mining in Biomedicine. ................................................................................................................................................................................................................................................. Editing Knowledge Bases The development of a technique called WYS/WYM ("What you see is what you meant"), which allows a subject matter (i.e. domain) expert to author complex knowledge bases through an ordinary natural langiage document rather than a knowledge representation or database language or relatively unfamiliar diagram. ................................................................................................................................................................................................................................................. PAST PROJECTS: Below is a list of projects that I have been involved with in the past: To return to the top of this page, please click here. ................................................................................................................................................................................................................................................. Multilingual Natural Language Generation Tools for authoring software manuals in English and French (DRAFTER) and in Bulgarian, Czech, English and Russian; (AGILE), administrative forms in English, Italian and German (GIST); and Pharmaceutical documents in English, French, German and Italian (PILLS). ................................................................................................................................................................................................................................................. Document Structure Theoretical work on the relation between the wording of a text and its graphical presentation, implemented in a system called ICONOCLAST, which generates texts with accompanying layout. ................................................................................................................................................................................................................................................. A Reference Architecture For Natural Language Generation The development of a framework called RAGS for describing the architecture of natural language generation systems, facilitating sharing of resources and comparative evaluation of different approaches. ................................................................................................................................................................................................................................................. *Generating Nominal Expressions* The development of a general purpose computational tool, GNOME, for generating appropriate nominal expressions. ................................................................................................................................................................................................................................................ Back to Top of Page