A Naive Bayes classifier for automatic correction of preposition and determiner errors in ESL text

Gerard Lynch (1) , Erwan Moreau (1) , Carl Vogel (1)

1 School of Computer Science and Statistics [Dublin]

This is the report for the CNGL ILT3 team entry to the HOO shared task. A Naive-Bayes-based classifier was used in the task which involved error detection and correction in ESL exam scripts. Our system placed 11th out of 14 teams for the detection and recognition tasks and 11th out of 13 teams for the correction task on the based on f-score for both preposition and determiner errors.

Domains: Document and Text Processing

Gerard Lynch, Erwan Moreau, Carl Vogel. A Naive Bayes classifier for automatic correction of preposition and determiner errors in ESL text. Seventh Workshop on Building Educational Applications Using NLP, Jun 2012, Montréal, Canada. pp.257--262. ⟨hal-00711273⟩