A Comparison Of Corpus-Based Techniques For Restoring Accents In Spanish And French Text

David Yarowsky 1994


Compares various methods for restoring accents:

  • baseline (most frequent)
  • n-gram tagger
  • bayesian classifier
  • decision lists

In his evaluation, he looks at a couple different cases, and talks about why different methods would be good for different cases.

Overall, the paper might be a decent read to see an example of these methods, but doesn't really show anything new..