[1]王 辉,潘俊辉,王浩畅,等.基于深度学习的中文语法错误诊断方法研究[J].计算机技术与发展,2020,30(11):69-73.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 013]
　WANG Hui,PAN Jun-hui,WANG Hao-chang,et al.Research on Chinese Grammar Error Diagnosis Method Based on Deep Learning[J].,2020,30(11):69-73.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 013]
点击复制

基于深度学习的中文语法错误诊断方法研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
30
期数:
2020年11期
页码:
69-73
栏目:
智能、算法、系统工程
出版日期:
2020-11-10

文章信息/Info

Title:
Research on Chinese Grammar Error Diagnosis Method Based on Deep Learning
文章编号:
1673-629X(2020)11-0069-05
作者:
王 辉1; 潘俊辉1; 王浩畅1; 张 强1; 张 岩1; Marius. Petrescu2
1. 东北石油大学 计算机与信息技术学院,黑龙江 大庆 163318; 2. 普罗莱斯蒂石油天然气大学,罗马尼亚 什蒂市 100680
Author(s):
WANG Hui1; PAN Jun-hui1; WANG Hao-chang1; ZHANG Qiang1; ZHANG Yan1; Marius. Petrescu2
1. School of Computer and Information Technology,Northeast Petroleum University,Daqing 163318,China; 2. Petroleum-Gas University of Ploiesti,Ploiesti 100680,Romania
关键词:
深度学习; 条件随机场; 长短期记忆网络; 注意机制; 语法错误诊断
Keywords:
deep learning; CRF; LSTM; attention mechanism; grammar error diagnosis
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2020. 11. 013
摘要:
随着中国国际影响力的日益提高和汉语国际地位的提升,学习和使用汉语的国际学者越来越多。 中文文本校对技术有助于各个领域处理所涉及到的文本错误,其中中文语法错误诊断是中文计算机辅助学习的研究热点之一。鉴于此,根据中文语法错误诊断的特点,通过分析现有中文语法错误诊断方法存在的问题,提出一种基于注意机制的双向长短期记忆网络(BI-LASM-ATT)与条件随机场(CRF)相结合的模型应用于中文语法错误诊断研究。 该模型采用 jieba 分词技术对数据进行分词和词性标注等预处理工作,利用 Skip-gram 模型得到词向量表示,作为 BI-LSTM-ATT 模型的词嵌入层,获取到两个方向上的长距离信息提供给 CRF 模型进行序列标注。 在 NLPCC2018 的 TASK2 提供的数据集上的实验结果表明,该模型对比传统语法错误诊断模型,在中文语法错误诊断的 Accuracy、精确率、召回率和 F_meature 方面均有明显提高。
Abstract:
With the increasing international influence of China and the promotion of the international status of Chinese,more and more international scholars are learning and using Chinese. The Chinese text automatic proofreading technology is helpful to deal with the text errors involved in various fields,among which Chinese grammar error diagnosis is one of the research hotspots in Chinese computer-aided learning. Based on this,according to the characteristics of Chinese grammar error diagnosis,after the problems existing in the existing Chinese grammar error diagnosis methods are analyzed,a model of bidirectional long-term memory network (BI-LSTM-ATT) and conditional random field (CRF) is proposed based on attention mechanism for Chinese grammar error diagnosis. In this model,the jieba is used as data preprocessing of word segmentation and POS tagging,and the Skip-gram model is used to get word vector representation as word embedding layer of BI-LSTM-ATT to capture long-distance context information in two directions for sequence labeling of the CRF. The experiments are carried out in the data set from NLPCC2018 TASK2,which show that the proposed model has significantly higher accuracy,precision,recall,and F_meature than traditional model of grammar error diagnosis.

相似文献/References:

[1]闵华清 黄欣欣 罗荣华.基于激光和视觉信息的机器人目标跟踪方法[J].计算机技术与发展,2010,(04):113.
　MIN Hua-qing,HUANG Xin-xin,LUO Rong-hua.Robot Target Tracking Approach Based on Laser and Vision Information[J].,2010,(11):113.
[2]张春元.基于条件随机场的文本分类模型[J].计算机技术与发展,2011,(07):77.
　ZHANG Chun-yuan.Text Categorization Model Based on Conditional Random Fields[J].,2011,(11):77.
[3]邱莎[] 阿圆 王付艳 丁海燕.基于统计的中文地名自动识别研究[J].计算机技术与发展,2011,(11):35.
　QIU Sha,A Yuan,WANG Fu-yan,et al.Study on Automatic Recognition of Chinese Location Names Based on Statistical Method[J].,2011,(11):35.
[4]楼博文,许歆艺,蔡根,等.智能信息系统中手机产品评论的情感倾向分析[J].计算机技术与发展,2013,(12):22.
　LOU Bo-wen[],XU Xin-yi[],CAI Gen[],et al.Analysis on Sentiment Orientation of Mobile Phone Product Reviews in Intelligent Information System[J].,2013,(11):22.
[5]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(11):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[6]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(11):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[7]黄法秀,张世杰,吴志红,等.数据增广下的人脸识别研究[J].计算机技术与发展,2020,30(03):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
　HUANG Fa-xiu,ZHANG Shi-jie,WU Zhi-hong,et al.Research on Face Recognition Based on Data Augmentation[J].,2020,30(11):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
[8]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(11):19.
[9]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(11):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
[10]贺飞翔,赵启军. 基于深度学习的头部姿态估计[J].计算机技术与发展,2016,26(11):1.
　HE Fei-xiang,ZHAO Qi-jun. Head Pose Estimation Based on Deep Learning[J].,2016,26(11):1.

更新日期/Last Update: 2020-11-10