汉语复句关系识别是对复句语义关系的识别,复句关系类别的自动识别对促进语言学和中文信息处理的研究有重要的价值。因果类复句是使用频率最高的复句,文中以二句式有标广义因果复句为研究对象, 使用语言技术平台LTP 进行依存句法分析, 获得词性、依存父节点的词序、与父节点的依存关系等特征,将特征的不同组合与预训练的词向量拼接,得到新的向量,将新的向量输入到 DPCNN 模型中来进行关系类别识别。通过实验对提出的方法进行检验,实验结果显示: 与未融合任何特征相比,DPCNN模型中融合语句特征使实验结果的指标均有提升,表明融合语句特征能取得更好的识别效果。在各种特征组合中,融合POS特征组合得到的准确度和F1值最高, 分别为98.41%, 98.28%。
Abstract
The classification of relation categories of Chinese complex sentences is to identify the semantic relation between clauses. The automatic classification of complex sentence relation category has important research values in linguistic studies and Chinese information processing. This paper explores the relation classification of marked generalized causal complex sentences with two clauses, which are the most frequently used complex sentences in Chinese articles. LTP(Language Technology Platform) is used to analyze dependency syntax to obtain features such as part of speech, word order of dependency parent node and dependency relationship with parent node. Different combinations of features are embedded with pre-trained word vector to obtain new vectors. The new vector is input into DPCNN model to classify the relation of causal complex sentences. Experimental results show that compared with the model without additional features, the fusion of sentence features makes the DPCNN model more effective. In various feature combinations, POS feature fusion has the highest accuracy and F1 value, which are 98.41% and 98.28% respectively.
关键词
因果类复句 /
关系识别 /
词向量 /
DPCNN模型 /
依存句法
{{custom_keyword}} /
Key words
causal complex sentence /
relation classification /
word vector /
DPCNN model /
dependency syntax
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Joty S, Guzmn F, Mrquez L I, et al. Using discourse structure for machine translation evaluation[C]//Proceedings of the ACL Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, 2014: 687-698.
[2] Verberne S, Boves L, Oostdijk N, et al. Evaluating discourse-based answer extraction for why -question answering[C]//Proceedings of the ACM SIGIR, 2007: 735-736.
[3] Huttunen S, Vihavainen A, Von Etter P, et al. Relevance prediction in information extraction using discourse and lexical features[C]//Proceedings of the 18th Nordic Conference of Computational Linguistics, 2011: 114-121.
[4] 徐凡, 朱巧明, 周国栋. 篇章分析技术综述[J]. 中文信息学报, 2013, 27(3):20-33.
[5] 严为绒, 徐扬, 朱珊珊,等. 篇章关系分析研究综述[J]. 中文信息学报, 2016, 30(4):1-11.
[6] Rong L. An overview of the study on Chinese cause-effect complex sentence [J]. Journal of Changchun Normal University, 2011, 30(9): 47-51.
[7] 石翠. 依存句法分析研究综述[J]. 智能计算机与应用, 2013, 3(006): 47-49.
[8] 杨进才, 涂馨丹, 沈显君,等. 基于依存关系规则的汉语复句关系词自动识别[J]. 计算机应用研究, 2018, 035(6): 1756-1760.
[9] 杨进才, 罗越群, 陈忠忠, 等. 汉语复句关系词的依存树特征分析[J]. 计算机与数字工程, 2017, 45(8): 1569-1573.
[10] 杨进才, 陈忠忠, 沈显君, 等. 二句式非充盈态有标复句关系类别的自动标志[J]. 计算机应用研究, 2017(10):2950-2953.
[11] Huang H, Chang T, Chen H, et al. Interpretation of Chinese discourse connectives for explicit discourse relation recognition[C]//Proceedings of the 25th International Conference on Computational Linguistics,2014: 632-643.
[12] 孙凯丽, 邓沌华, 李源, 等. 基于句内注意力机制多路CNN的汉语复句关系识别方法[J]. 中文信息学报, 2020(6), 34(6): 9-17.
[13] Johnson R, Zhang T. Deep pyramid convolutional neural networks for text categorization[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017, 1: 562-570.
[14] 奚雪峰,周国栋.面向自然语言处理的深度学习研究[J].自动化学报,2016,42(10): 1445-1465.
[15] 杨进才, 汪燕燕, 曹元,等. 关系词非充盈态复句的特征融合CNN关系识别方法[J]. 计算机系统应用, 2020, 029(6):224-229.
[16] 吕叔湘, 朱德熙. 语法修辞讲话[M]. 上海: 开明书店, 1952.
[17] 黄伯荣, 廖序东. 现代汉语[M]. 3版. 北京: 高等教育出版社, 2002.
[18] 邢福义. 汉语复句研究[M]. 北京: 商务印书馆, 2001.
[19] Lin D K. A dependency-based method for evaluating broad-coverage parsers[J]. Natural Language Engineering, 1998, 4(2): 97-114.
[20] 刘海涛. 依存语法的理论与实践[M]. 北京: 科学出版社, 2009.
[21] 刘挺, 车万翔, 李正华. 语言技术平台[J]. 中文信息学报, 2011, 25(6): 53-63.
[22] Mikolov T, Sutskever I, Chen K, et al. Distributed representations of words and phrases and their compositionality[J]. Advances in Neural Information Processing Systems, 2013, 26:3111-3119.
[23] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2016: 770-778.
[24] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research. 2014: 1929-1958.
[25] Caruana R, Lawrence S, Giles L. Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping[C]//Proceedings of the 13th International Conference on Neural Information Processing Systems. 2001: 381-387.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家社会科学基金(19BYY092)
{{custom_fund}}
PDF(1994 KB)
