Difference between revisions of "Ideas for Google Summer of Code/Unsupervised weighting of automata"

From Apertium
Jump to navigation Jump to search
(Created page with "foo")
 
Line 1: Line 1:
  +
foo
 
  +
  +
==Coding challenge==
  +
  +
* Install [[HFST]]
  +
* Install [[lttoolbox]]
  +
* Define an evaluation metric
  +
* Perform a baseline experiment using a tagged corpus:
  +
** Select a language
  +
** Split the corpus into 90% training, 10% testing (or use existing test/train split)
  +
** Use the Apertium morphological analyser to analyse the test data
  +
** Rank the analyses produced using the training data
  +
** Compare this ranking to the default order from the transducer, and to a "random" ranking
  +
  +
  +
  +
  +
[[Category:Ideas for Google Summer of Code|Unsupervised weighting of automata]]

Revision as of 17:02, 29 March 2017


Coding challenge

  • Install HFST
  • Install lttoolbox
  • Define an evaluation metric
  • Perform a baseline experiment using a tagged corpus:
    • Select a language
    • Split the corpus into 90% training, 10% testing (or use existing test/train split)
    • Use the Apertium morphological analyser to analyse the test data
    • Rank the analyses produced using the training data
    • Compare this ranking to the default order from the transducer, and to a "random" ranking