Past (academic) research projects

  • performant speaker diarization (while at AWS)
  • address extraction from unstructured document (at Teebly)
  • content extraction from HTML pages (at Skim Technologies/Deeper Insights)
  • Evaluation of methods for compositional distributional semantics (PhD thesis, 2015). A copy of my thesis can be found here.
  • Automatic moderation of online message boards (2011)

Detailed descriptions coming soon.