write evaluation scripts for comparing reference annotations and model annotations

[mnaydan]

• Convert @mnaydan's annotations to the desired annotation format (mainly determine corresponding span indices).
• Get passim results for test set with default parameters
  • "Raw" passim output (i.e. various files within a specific (top-level) output directory)
  • Standardized passim output
• Write script(s) for computing evaluation metrics for passim results (against @mnaydan's annotations)
• Create a document that reports on results
  • Include original/aligned excerpts for visual inspection
  • Include scores for evaluation metrics