Automatic morphological analysis of learner Hungarian

Scott Ledbetter and Markus Dickinson

Proceedings of the Tenth Workshop on Innovative Use of NLP for Building Educational Applications

In this paper, we describe a morphological analyzer for learner Hungarian, built upon limited grammatical knowledge of Hungarian. The rule-based analyzer requires very few resources and is flexible enough to do both morphological analysis and error detection, in addition to some unknown word handling. As this is work-in-progress, we demonstrate its current capabilities, some areas where analysis needs to be improved, and an initial foray into how the system output can support the analysis of interlanguage grammars.


Electronically available file formats:


Bibtex entry:

@InProceedings{ledbetter:dickinson:15,
  author    = {Ledbetter, Scott  and  Dickinson, Markus},
  title     = {Automatic morphological analysis of learner Hungarian},
  booktitle = {Proceedings of the Tenth Workshop on Innovative Use of NLP for Building Educational Applications},
  month     = {June},
  year      = {2015},
  address   = {Denver, CO},
  pages     = {31--41},
  url       = {http://cl.indiana.edu/~md7/papers/ledbetter-dickinson15.html}
}