An english subordinate clause connective correction model based on genetic algorithm and k-nearest neighbor algorithm
Guimin Huang, Chuang Kuo Wu, Sirui Huang, Hongtao Zhu, Ruyu Mo, Ya Zhou · 2017
In English writing, English learners will inevitably make a variety of grammatical mistakes, especially in English subordinate clause connective. To alleviate high error rate of connective in subordinate clauses of Chinese students' English writing, an automatic error correction model for English subordinate clause connective is studied and implemented from the perspective of machine learning — genetic algorithm (GA) and k-nearest neighbor (KNN) algorithm combination model. Firstly, an automatic feature selection algorithm based on GA is adopted to reduce time consuming and space cost, and to improve the accuracy of connective error correction. Secondly, through comparing the Naive Bayes, decision tree, maximum entropy and KNN algorithm, KNN algorithm is found better while classifying the connectives. Finally, we compared the performance of several hybrid models, which combine different machine learning algorithms with GA. This proves that the combination of GA and KNN algorithm is optimal.