How It Works

The overall workplan is:

  • extract documents from the Open literature or contributed documents
  • locate and extract the paragraphs containing chemical reactions (experiment.xml)
  • parse the paragraphs using Lezan Hawizy's ChemicalTagger to give POS an Chemistry-based trees (chemicalTagger.xml)
  • add CML chemical semantics to these (chemicalTreeBank.xml)
  • extract the reaction data (not yet written)
  • process this to RDF (ditto)
  • ingest into triple store
  • query the triple store to answer green questions
  • present results

It's ambitious, but possible

Unless otherwise stated, the content of this page is licensed under Creative Commons Attribution-ShareAlike 3.0 License