We present a novel approach to grammatical error correction based on Alternating Structure Optimization. As part of our work, we introduce the NUS Corpus of Learner English (NUCLE), a fully annotated one million words corpus of learner English available for research purposes. We conduct an extensive evaluation for article and preposition errors using various feature sets. Our experiments show that our approach outperforms two baselines trained on non-learner text and learner text, respectively. Our approach also outperforms two commercial grammar checking software packages. 1

Abstract not found

Abstract not found

We extend the n-gram-based data-driven prediction approach (Elghafari, Meurers and Wunsch, 2010) to identify function word errors in non-native academic texts as part of the Helping Our Own (HOO) Shared Task. We focus on substitution errors for four categories: prepositions, determiners, conjunctions, and quantifiers. These error types make up 12 % of the errors annotated in the HOO training data. In our best submission in terms of the error detection score, we detected 67 % of preposition and determiner substitution errors, 40% of conjunction substitution errors, and 33% of quantifier substitution errors. For approximately half of the errors detected, we were also able to provide an appropriate correction. 1

Which annotations? How?