Predicting Learner Levels for Online Exercises of Hebrew

Markus Dickinson, Sandra Kübler, and Anthony Meyer

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

We develop a system for predicting the level of language learners, using only a small amount of targeted language data. In particular, we focus on learners of Hebrew and predict level based on restricted placement exam exercises. As with many language teaching situations, a major problem is data sparsity, which we account for in our feature selection, learning algorithm, and in the setup. Specifically, we define a two-phase classification process, isolating individual errors and linguistic constructions which are then aggregated into a second phase; such a two-step process allows for easy integration of other exercises and features in the future. The aggregation of information also allows us to smooth over sparse features.

Electronically available file formats:

Bibtex entry:

  author    = {Dickinson, Markus  and  K\"{u}bler, Sandra  and  Meyer, Anthony},
  title     = {Predicting Learner Levels for Online Exercises of Hebrew},
  booktitle = {Proceedings of the Seventh Workshop on Building Educational Applications Using NLP},
  month     = {June},
  year      = {2012},
  address   = {Montr\'{e}al, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {95--104},
  url =  {}