Paper: Evaluating performance of grammatical error detection to maximize learning effect

ACL ID C10-2103
Title Evaluating performance of grammatical error detection to maximize learning effect
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010
Authors

This paper proposes a method for eval- uating grammatical error detection meth- ods to maximize the learning effect ob- tained by grammatical error detection. To achieve this, this paper sets out the following two hypotheses imperfect, rather than perfect, error detection max- imizes learning effect; and precision- oriented error detection is better than a recall-oriented one in terms of learning ef- fect. Experiments reveal that (i) precision- oriented error detection has a learning ef- fect comparable to that of feedback by a human tutor, although the rst hypothesis is not supported; (ii) precision-oriented er- ror detection is better than recall-oriented in terms of learning effect; (iii) a0 -measure is not always the best way of evaluating error detection methods.