Sandra Williams

Sandra Williams

Visiting Research Fellow

Research Fellow in Natural Language Generation

  • Generating Maths Word Problems and Solutions I am investigating automatic generation of mathematical word problems with hints for solution methods in easy-to-follow steps, similar to those produced by basic-skills tutors, see Math Stories. I am keen to collaborate on this research with psychologists, maths teachers, educational researchers, and intelligent tutoring researchers.
  • Rendering the semantic web accessible to people who want to create or modify semantic content but do not know ontology languages and logics. My role in the SWAT project was to provide natural language support for ontology verbalisation and authoring. I developed grammars and discourse structuring algorithms for the SWAT verbaliser and a tool to extract ontology identifier names from text.
  • Computer-generation of numerical quantity expressions. Numerical quantities are often presented poorly (especially in the media) which frustrates numerate people who are not given enough information while at the same time it perplexes innumerate people who do not understand basic mathematical concepts. I believe that it is possible to vary descriptions of numerical quantities to suit different audiences, situations and writing styles. I recently completed an ESRC Small Project, NumGen, to investigate feasibility and potential areas for future research. I am currently seeking opportunities for follow-up project proposals.

Students

  • Sharon Moyo, Ph.D. student (co-supervisor)
  • Tu Anh Nguyen, Ph.D. student (co-supervisor)
  • Stephen Taylor, M.Sc. student (specialist advisor)
  • Susana Bautista Blasco, Summer Intern. 2010 (supervisor)

Email:
[javascript protected email address]