Grammatical Error Correction Using Feature Selection and Confidence Tuning

This paper proposes a novel approach to resolve the English article error correction problem, which accounts for a large proportion in grammatical errors. Most previous machine learning based researches empirically collected features which may bring about noises and increase the computational complexity. Meanwhile, the predicted result is largely affected by the threshold setting of a classifier which can easily lead to low performance but hasn’t been well developed yet. To address these problems, we employ genetic algorithm for feature selection and confidence tuning to reinforce the motivation of correction. Comparative experiments on the NUCLE corpus show that our approach could efficiently reduce feature dimensionality and enhance the final F₁ value for the article error correction problem.