Modifying Corpus Annotation to Support the Analysis of Learner Language

Markus Dickinson and Chong Min Lee

CALICO Journal

A crucial question for automatically analyzing learner language is which grammatical information is relevant and useful for learner feedback. Based on knowledge about how learner language varies in its grammatical properties, we propose a framework for re-using analyses found in corpus annotation and illustrate its applicability to Korean postpositional particles. Simple transformations of the corpus annotation allow one to quickly use state-of-the-art parsing methods.

Electronically available file formats:

Note: The electronic version of the publication linked on this page is the last version I had the copyright for. Where a publisher copyedited and/or typeset the papers, the electronic copies linked here are NOT identical to the officially published version, which should be used for any quotes, references to page numbers, etc.

Bibtex entry: 

@Article{dickinson:lee:09,
  author =  {Markus Dickinson and Chong Min Lee},
  title =   {Modifying Corpus Annotation to Support the Analysis of
             Learner Language},
  journal = {CALICO Journal},
  year =    {2009},
  volume =  {26},
  number =  {3},
  pages =   {545--561},
  month =   {May},
  note =    {\url{http://jones.ling.indiana.edu/~mdickinson/papers/dickinson-lee09.html}}
}