Grammar Error Correction in English-Chinese Translation using Gaussian Mixture Distribution based K-Means Clustering

The translation process involved English – chinses grammar error correction by using Machine Learning (ML) technique is analysis basic principles and particular strategies of language translation. However, sensitive to analysis English – chinses grammar correction which cause the model to perform less accuracy, when data is noisy due to difficult to analysis the text feature. This paper, proposed Gaussian Mixture Distribution based on K-means clustering (GMD based K-means) technique for classification is efficiently classify the error correction it help to achieve the better accuracy. The GMD based K-means is handle overlapping clusters more effectively because they model data distribution using Gaussian distribution which capture the text feature efficiently. Initially data obtained from English-Chinese Bilingual Parallel Corpora (ECBPC) dataset and pre-processing including normalization is used to address the large gap between values of different dimension in text data. The feature extraction using Term Frequency-Inverse Document Frequency (TF-IDF) is applied to reduce Nosie in data and improve quality of feature representation. The proposed GMD based K-means method is evaluated using ECBPC data achieving a higher accuracy of 92.45% respectively. The existing techniques such as Support Vector Machine (SVM) and Generalized LR (GLR) are evaluated of proposed method.