Proceedings of the NAACL-HLT 2012 workshop on innovative use of NLP for building educational applications pages:263-271
NAACL-HLT 2012 workshop on innovative use of NLP for building educational applications location:Montreal, Canada date:7 June 2012
In this paper we describe the technical implementation of our system that participated in the Helping Our Own 2012 Shared Task (HOO-2012). The system employs a number of preprocessing steps and machine learning
classifiers for correction of determiner and preposition errors in non-native English texts. We use maximum entropy classifiers trained on the provided HOO-2012 development data and a large high-quality English text collection.
The system proposes a number of highly probable corrections, which are evaluated by a language model and compared with the original
text. A number of deterministic rules are used to increase the precision and recall of the system. Our system is ranked among the three best performing HOO-2012 systems with a precision of 31.15%, recall of 22.08% and F1-score of 25.84% for correction of determiner
and preposition errors combined.