面向中文的端到端多实体关系提取研究
End-to-End Multi-Entity Relationship Extraction for Chinese Text
DOI: 10.12677/CSA.2019.912251, PDF,   
作者: 杨 浩：北京邮电大学网络技术研究院，北京
关键词: 实体关系提取；端到端；BiLSTM；多实体对；Entity Relation Extraction； End-to-End； BiLSTM； Multiple Entity Pairs
摘要: 关系提取可以获得文本中的关键信息。实体关系提取是在非结构化文本识别出实体并提取出实体对之间关系的方法。针对传统的关系提取借助外部NLP工具和局部分类等问题，端到端的实体关系提取模型可以减少管道模型之间的错误传播，获得更好的效果。设计一种基于BiLSTM的端到端的实体关系提取模型，通过决策对应实体和关系的可能性，解决中文文本中的多实体对的问题。在中文文本上，实现了3种实体识别10类关系提取。实验结果表明该方法无需人工构建复杂特征即可得到较好的多实体对关系抽取效果。
Abstract: Relationship extraction can obtain key information in the text. Entity relationship extraction is a method to identify entities in unstructured text and extract the relationships between entity pairs. For the traditional relationship extraction with the help of external NLP tools and local classification, the end-to-end entity relationship extraction model can reduce the error propagation between pipeline models and obtain better results. An end-to-end entity relationship extraction model based on BiLSTM was designed to solve the problem of multiple entity pairs in Chinese texts by making decisions on the possibility of corresponding entities and relationships. In Chinese text, three kinds of entity recognition and 10 kinds of relation extraction are realized. The experimental results show that this method can achieve a better result of multi-entity relation extraction without manual construction of complex features.
文章引用：杨浩. 面向中文的端到端多实体关系提取研究[J]. 计算机科学与应用, 2019, 9(12): 2256-2265. https://doi.org/10.12677/CSA.2019.912251

参考文献

[1] 王超. 基于深度学习的中文微博人物关系图谱的研究与实现[D]: [硕士学位论文]. 武汉: 武汉邮电科学研究院, 2018.
[2] 唐敏. 基于深度学习的中文实体关系抽取方法研究[D]: [硕士学位论文]. 成都: 西南交通大学, 2018.
[3] 谢星辰. 互联网人物属性识别与融合方法研究[D]: [硕士学位论文]. 成都: 电子科技大学, 2018.
[4] 黄蓓静. 深度学习技术在中文人物关系抽取中的应用研究[D]: [硕士学位论文]. 上海: 华东师范大学, 2017.
[5] Mintz, M., Bills, S., Snow, R. and Jurafsky, D. (2009) Distant Supervision for Relation Extraction without Labeled Data. Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, Singapore, 2-7 August 2009, 1003-1011. [Google Scholar] [CrossRef] 
[6] Culotta, A., McCallum, A. and Betz, J. (2006) Integrating Probabil-istic Extraction Models and Data Mining to Discover Relations and Patterns in Text. Proceedings of the Main Conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Lin-guistics, New York, 4-9 June 2006, 296-303. [Google Scholar] [CrossRef] 
[7] Doddington, G.R., Mitchell, A., Przybocki, M.A., et al. (2004) The Automatic Content Extraction (ACE) Program-Tasks, Data, and Evaluation. Proceedings of the Fourth International Conference on Language Resources and Evaluation, Lisbon, Portugal.
[8] Zelenko, D., Aone, C. and Richardella, A. (2003) Kernel Methods for Relation Extraction. Journal of Machine Learning Research, 3, 1083-1106.
[9] Gábor, K., Buscaldi, D., Schumann, A.K., et al. (2018) Semeval-2018 Task 7: Semantic Relation Extraction and Classification in Scientific Papers. Proceedings of The 12th International Workshop on Semantic Evaluation, New Orleans, LA, 679-688. [Google Scholar] [CrossRef] 
[10] Zhang, M., Zhang, Y. and Fu, G. (2017) End-to-End Neural Relation Extraction with Global Optimization. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, 1730-1740. [Google Scholar] [CrossRef] 
[11] Ammar, W., Peters, M., Bhagavatula, C., et al. (2017) The AI2 System at SemEval-2017 Task 10 (ScienceIE): Semi-Supervised End-to-End Entity and Relation Extraction. Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), Vancouver, 592-596. [Google Scholar] [CrossRef] 
[12] Ren, X., Wu, Z., He, W., et al. (2017) CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases. Proceedings of the 26th International Confer-ence on World Wide Web, Perth, Australia, 3-7 April 2017, 1015-1024. [Google Scholar] [CrossRef] 
[13] Rink, B. and Harabagiu, S. (2010) Utd: Classifying Semantic Rela-tions by Combining Lexical and Semantic Resources. Proceedings of the 5th International Workshop on Semantic Evalu-ation, Los Angeles, CA, 15-16 July 2010, 256-259.
[14] Tu, C., Zhang, Z., Liu, Z. and Sun, M. (2017) TransNet: Translation-Based Network Representation Learning for Social Relation Extraction. Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, 2864-2870. [Google Scholar] [CrossRef] 
[15] 司文豪, 贾雷萍, 戚银城. 基于卷积神经网络的中文人物关系抽取方法[J]. 计算机与现代化, 2018(9): 17-20.
[16] Santos, C.N., Xiang, B. and Zhou, B. (2015) Classifying Relations by Ranking with Convolutional Neural Networks. arXiv preprint arXiv:1504.06580.
[17] Nguyen, T.H. and Grishman, R. (2015) Relation Extraction: Perspec-tive from Convolutional Neural Networks. Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing, Denver, Co, 39-48. [Google Scholar] [CrossRef] 
[18] Meng, L. and Wu, B. (2017) Core Discovery and Relation Extraction in Organization Profiling. 2017 13th International Conference on Semantics, Knowledge and Grids, Beijing, 13-14 August 2017, 219-222. [Google Scholar] [CrossRef] 
[19] Rotsztejn, J., Hollenstein, N. and Zhang, C. (2018) ETH-DS3Lab at SemEval-2018 Task 7: Effectively Combining Recurrent and Convolutional Neural Networks for Relation Classification and Extraction. arXiv Preprint arXiv:1804.02042. [Google Scholar] [CrossRef] 
[20] Peng, N., Poon, H., Quirk, C., Toutanova, K. and Yih, W.-T. (2017) Cross-Sentence N-Ary Relation Extraction with Graph LSTMS. arXiv Preprint arXiv:1708.03743. [Google Scholar] [CrossRef] 
[21] Zhang, D.X. and Wang, D. (2015) Relation Classification via Recurrent Neural Network. arXiv Preprint arXiv:1508.01006.
[22] Zhou, P., Shi, W., Tian, J., et al. (2016) Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2, 207-212. [Google Scholar] [CrossRef] 
[23] Miwa, M. and Bansal, M. (2016) End-to-End Relation Extraction Using LSTMS on Sequences and Tree Structures. arXiv Preprint arXiv:1601.00770. [Google Scholar] [CrossRef] 
[24] Zheng, S., Hao, Y., Lu, D., et al. (2017) Joint Entity and Relation Ex-traction Based on a Hybrid Neural Network. Neurocomputing, 257, 59-66. [Google Scholar] [CrossRef]