基于深度学习的古汉语命名实体识别研究
Ancient Chinese Named Entity Recognition Based on Deeping Learning
DOI: 10.12677/CSA.2020.107140, PDF,  被引量    国家自然科学基金支持
作者: 卓玛措, 桑杰端珠, 才让加：青海师范大学藏文信息处理教育部重点实验室，青海 西宁；青海省藏文信息处理与机器翻译重点实验室，青海 西宁
关键词: 神经网络模型；古汉语；命名实体识别；条件随机场；Neural Network Model； Ancient Chinese； Named Entity Recognition； Conditional Random Field
摘要: 命名实体识别是自然语言处理的基础任务之一。而目前中文命名实体识别研究大多是面向现代汉语的，针对古汉语的这方面研究工作涉及较少。因此，本文以《战国策》为例，根据古汉语独特的子语言特征，利用网格长短期记忆(Lattice LSTM)神经网络构建命名实体识别模型以解决古汉语中的信息提取问题。实验结果表明，Lattice LSTM能够学会从语境中自动找到所有与词典匹配的词汇，以取得较好的命名实体识别性能。实验结果中的F1值达到92.16%。
Abstract: Named entity recognition is one of the basic tasks of natural language processing. At present, the research on Chinese named entities recognition is mostly for modern Chinese, and the research on it for ancient Chinese is less involved. So in this paper, taking the War State Policy as an example and according to the characteristics of ancient Chinese text, we use the Lattice Long and Short-Term memory (Lattice LSTM) neural network to construct a named entity recognition model to solve the problem of information extraction of ancient Chinese. Experiment result shows that Lattice LSTM can learn to automatically find all the dictionary-matched words from the context to achieve better named entity recognition performance. The F1 value reaches 92.16%.
文章引用：卓玛措, 桑杰端珠, 才让加. 基于深度学习的古汉语命名实体识别研究[J]. 计算机科学与应用, 2020, 10(7): 1359-1366. https://doi.org/10.12677/CSA.2020.107140

参考文献

[1] Hammerton, J. (2003) Named Entity Recognition with Long Short-Term Memory. In: Conference on Natural Language Learning, Association for Computational Linguistics, Stroudsburg, 172-175. [Google Scholar] [CrossRef] 
[2] 张海楠, 伍大勇, 刘悦, 等. 基于深度神经网络的中文命名实体识别[J]. 中文信息学报, 2017, 31(4): 28-35.
[3] Ma, X. and Hovy, E. (2016) End-to-End Sequence Labeling via Bi-Directional LSTM-CNNs-CRF. Proceedings of the 54th Annual Meeting of the Association for Computational Lin-guistics, Volume 1: Long Papers, Berlin, August 2016, 1064-1074. [Google Scholar] [CrossRef] 
[4] Chiu, J.P.C. and Nichols, E. (2016) Named Entity Recognition with Bi-directional LSTM-CNNs. Transactions of the Association for Computational Linguistics, 4, 357-370. [Google Scholar] [CrossRef] 
[5] Lample, G., Ballesteros, M., Subramanian, S., et al. (2016) Neural Ar-chitectures for Named Entity Recognition. Proceedings of NAACL-HLT 2016, San Diego, 12-17 June 2016, 260-270. [Google Scholar] [CrossRef] 
[6] Nothman, J., Ringland, N., Radford, W., Murphy, T. and Curran, J.R. (2013) Learning Multilingual Named Entity Recognition from Wikipedia. Artificial Intelligence, 194, 151-175.
[7] Santos, C.N.D. and Guimarães, V. (2015) Boosting Named Entity Recognition with Neural Character Embeddings.
[8] 买买提阿依甫, 吾守尔•斯拉木, 帕丽旦•木合塔尔, 等. 基于BiLSTM-CNN-CRF模型的维吾尔文命名实体识别[J]. 计算机工程, 2018, 44(8): 230-236.
[9] 王洁, 张瑞东, 吴晨生. 基于GRU的命名实体识别方法[J]. 计算机系统应用, 2018, 27(9): 18-24.
[10] 李丽双, 郭元凯. 基于CNN-BLSTM-CRF模型的生物医学命名实体识别[J]. 中文信息学报, 2018, 32(1): 116-122.
[11] 周晓磊, 赵薛蛟, 刘堂亮, 宗子潇, 王其乐, 里剑桥. 基于SVM-BiLSTM-CRF模型的财产纠纷命名实体识别方法[J]. 计算机系统应用, 2019, 28(1): 245-250.
[12] 杨文明, 褚伟杰. 在线医疗问答文本的命名实体识别[J]. 计算机系统应用, 2019, 28(2): 8-14.
[13] He, J. and Wang, H. (2008) Chinese Named Entity Recognition and Word Segmentation Based on Character. Proceedings of the Sixth SIGHAN Workshop on Chinese Language Processing, Hyderabad, 11-12 January 2008, 128-132.
[14] Liu, Z., Zhu, C. and Zhao, T. (2010) Chinese Named Entity Recognition with a Sequence Labeling Approach: Based on Characters, or Based on Words? In: Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence, Springer, Berlin Heidelberg, 634-640. [Google Scholar] [CrossRef] 
[15] 杨培, 杨志豪, 罗凌, 林鸿飞, 王健. 基于注意机制的化学药物命名实体识别[J]. 计算机研究与发展, 2018, 55(7): 1548-1556.
[16] Li, H., Hagiwara, M., Li, Q., et al. (2014) Comparison of the Impact of Word Segmentation on Name Tagging for Chinese and Japanese. 2014 LREC, Reykjavik, 26-31 May 2014, 2532-2536.
[17] Chen, W., Zhang, Y. and Isahara, H. (2006) Chinese Named Entity Recognition with Conditional Random Fields. Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing, Sydney, 22-23 July 2006, 118-121.
[18] Dong, C., Zhang, J., Zong, C., et al. (2016) Character-Based LSTM-CRF with Radical-Level Features for Chinese Named Entity Recognition. In: Natural Language Understanding and Intelligent Applications, Springer, Cham, 239-250. [Google Scholar] [CrossRef] 
[19] Huang, Z., Xu, W. and Yu, K. (2015) Bidirectional LSTM-CRF Models for Sequence Tagging.
[20] Zhang, Y. and Yang, J. (2018) Chinese NER Using Lattice LSTM. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Volume 1: Long Papers, Melbourne, July 2018, 1554-1564. [Google Scholar] [CrossRef] 
[21] Graves, A. (2013) Generating Sequences with Recurrent Neural Net-works. Computer Science, 1-43.