Mark's PhD research work fell into two components
within the subfield of statistical language learning.
- Corpus-based compound noun analysis
- Data requirements for statistical language learners
He completed a PhD dissertation exploring both these areas in 1995.
You can view the abstract, download the
postscript,
or get the LaTeX source from the
computational and language E-print archive.
Further details about the research can be found in
Mark's published work. A personal
bibliography, including links to electronic copies of some
papers, is available.