skip to content

Department of Computer Science and Technology

  • Professor of Language and Information

Full website here: https://www.cl.cam.ac.uk/~sht25

Biography

1994 Diplom in Computer Science, University of Stuttgart

2000 PhD in Cognitive Science, Edinburgh University 

2000 Postdoc on Medical information retrieval at Columbia University with Kathy McKeown

2001 Lecturer Computer Laboratory, Cambridge University

2017 Professor of Language and Information, Cambridge University

Research

My area of research is methods for text understanding. In particular, I develop models of discourse structure and argumentation in scientific text, comprehension models for text summarisation, and models of human argumentation. I also work on how "folk logic" connects to linguistic expressions, and on explanatory models of metaphor. 

The logical structure of a text is an important dimension of its meaning, and several applications could profit from its analysis -- for instance text summarization, scientific search engines, improved bibliometrics, detection of "hot ideas" in a scientific field, and tools for better academic writing. I have proposed a discourse analysis called Argumentative Zoning or AZ, which is based on the recognition of the following phenomena: sentiment expressed towards cited work, ownership of ideas, and speech acts which express rhetorical statements typical for scientific argumentation. Co-reference between entities mentioned in text, and coherence of text pieces also plays an important role in my model. I am also interested in cognitive experiments to prove the use of this type of robust processing in a real user environment, particularly in task-based evaluations.

Contact Details

Room: 
GS14
Email: 

crsid at cam.ac.uk (crsid = sht25)