Semantic collocation word checking method

• Main Authors: TAN HUI, ZHU LIYE, XIE ZHENPING, LI YAN, XIA ZHENTAO, ZHANG SHUO
• Format: Patent
• Language: Chinese; English
• Published: 26.11.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention provides a semantic collocation word checking method, which comprises the following steps of: extracting collocation words from an article data set, and establishing a collocation dictionary; converting the to-be-judged text into a text vector; inputting the text vector into a deep learning model, inputting the text vector into an encoder for encoding by the deep learning model, and performing full connection layer processing on the encoded vector to obtain a judgment result of the text; and if it is judged that the matching words in the input to-be-judged text are matched correctly, enabling the output judgment result to be correct. According to the semantic collocation word checking method, the error detection accuracy, the error detection recall rate, the error detection F value and the error detection accuracy can reach 90% or above. 本发明提供一种语义搭配词检查方法，包括：对文章数据集进行搭配词提取，建立搭配词典；将待判断文本转化为文本向量；将文本向量输入深度学习模型，所述深度学习模型将文本向量输入编码器进行编码，将编码后的向量经过全连接层处理，得到文本的判断结果；若判断输入的待判断文本中搭配词搭配正确，则输出判断结果为正确。本发明的语义搭配词检查