基于多语法改错证据的英语语法校对  

English Grammar Proofreading Based on Multi Grammatical Error Correction Evidence

作　　者：宫昀[1] 华雪侠[1] GONG Yun;HUA Xue-xia(Xianyang Normal University,Xianyang 712000 China)

机构地区：[1]咸阳师范学院,陕西咸阳712000

出　　处：《自动化技术与应用》2024年第4期82-84,共3页Techniques of Automation and Applications

基　　金：咸阳市科技计划项目(L2023-ZDYF-SF-025);陕西省教育科学“十四五”规划课题(SGH22Y1419);陕西省教育科学“十四五”规划2021年度重点课题(SGH21Z14)。

摘　　要：为了实现高精度的英语语法校对,建立一套基于多语法改错假设的神经验证网络(VERNet)模型。通过该模型对语法改错假设和所输入的每一条句子加以拼接,基于各项假设之间的交互关系来获取语法改错证据。为证实该模型的有效性,在实验中通过VERNet模型对三个通用语法改错数据集进行校对处理。实验研究发现,该模型的语法改错质量显著优于各种不同类型的主流英语语法校对模型。In order to achieve high-precision English grammar proofreading,this study establishes a neural verification network(Vernet)model based on the multi grammar error correction hypothesis.Through this model,the grammar error correction hypothesis and each sentence input are spliced,and the grammar error correction evidence is obtained based on the interaction between various hypotheses.In order to verify the effectiveness of this model,three general syntax error correction data sets are proofread by Vernet model in the experiment.The experimental research shows that the grammar correction quality of this model is significantly better than that of various types of mainstream English grammar proofreading models.

关 键 词：神经验证网络 语法改错证据 注意力机制 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP391.1[自动化与计算机技术—控制科学与工程]