This paper explores the generation of ar- tificial errors for correcting grammatical mistakes made by learners of English as a second language. Artificial errors are in- jected into a set of error-free sentences in a probabilistic manner using statistics from a corpus. Unlike previous approaches, we use linguistic information to derive error generation probabilities and build corpora to correct several error types, including open-class errors. In addition, we also analyse the variables involved in the selec- tion of candidate sentences. Experiments using the NUCLE corpus from the CoNLL 2013 shared task reveal that: 1) training on artificially created errors improves pre- cision at the expense of recall and 2) dif- ferent types of linguistic information are better suited for correcting diff...

Click Here to View the Paper In XML Format