TY - GEN
T1 - An english subordinate clause connective correction model based on genetic algorithm and k-nearest neighbor algorithm
AU - Huang, Guimin
AU - Wu, Chuang
AU - Huang, Sirui
AU - Zhu, Hongtao
AU - Mo, Ruyu
AU - Zhou, Ya
N1 - Funding Information:
ACKNOWLEDGMENT This work is supported by the National Natural Science Foundation of China (No. 61662012) as well as the Foundation of Key Laboratory of Cognitive Radio and Information Processing, Ministry of Education (Guilin University of Electronic Technology, No. CRKL150105) and the scientific research & technological development Project of Guilin (No. 2016010406-3) and the Innovation Project of GUET Graduate Education (No. 2016YJCX16).
Publisher Copyright:
© 2017 IEEE.
PY - 2017
Y1 - 2017
N2 - 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.
AB - 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.
KW - Connective correction
KW - Feature selection
KW - Genetic algorithm
KW - Machine learning
UR - http://www.scopus.com/inward/record.url?scp=85048174102&partnerID=8YFLogxK
U2 - 10.1109/PIC.2017.8359561
DO - 10.1109/PIC.2017.8359561
M3 - Conference Proceeding
AN - SCOPUS:85048174102
T3 - Proceedings of 2017 International Conference on Progress in Informatics and Computing, PIC 2017
SP - 302
EP - 306
BT - Proceedings of 2017 International Conference on Progress in Informatics and Computing, PIC 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th International Conference on Progress in Informatics and Computing, PIC 2017
Y2 - 15 December 2017 through 17 December 2017
ER -