当前基于图神经网络的事件抽取模型无法很好解决长距离依赖问题,并且图的构造中没有考虑实体之间的关系,实体也需要结合文档中的多个句子进行推理。为解决这些问题,该文首先使用预训练模型RoBERTa对文档进行编码并输出所有句子的特征表示和文档的上下文信息嵌入表示,能更好地学习中文金融数据的语义特征。其次,构建一个包含文档节点和实体节点的全局图神经网络使不同节点和边的交互有更丰富的表示,加强了文档和实体信息之间的联系。最后,应用图卷积网络捕获了它们之间的全局交互得到实体级图,在此基础上通过改进的路径推理机制来推断实体之间的关系,更好地解决了长距离文档上下文感知表示和跨句子论元分散问题。在CFA数据集上进行了模型验证,实验结果表明,该文所提模型F1值优于对比模型,综合性能得到有效提升。
Abstract
Current event extraction models based on the graph neural network cannot properly process the long-distance dependency, and the relationships between entities are not considered in the construction of the graph. This paper proposes a document-level Chinese financial event extraction model based on RoBERTa and the global graph neural network. Firstly, the pre-training model RoBERTa is used to encode documents. The feature representation of all sentences and the embedded representation of document context information are output. Then a global graph neural network including document nodes and entity nodes is constructed to strengthen the relationships between documents and entities. Finally, the global interactions between them are captured by the graph convolution network to obtain the entity level graph. An improved path reasoning mechanism is applied to solve the long-distance context-aware representation and cross-sentence argument distribution. The experimental results on CFA dataset show that the proposed model achieves higher F1 scores than other models.
关键词
文档级事件抽取 /
图神经网络 /
图卷积网络 /
注意力机制
{{custom_keyword}} /
Key words
document-level event extraction /
graph neural network /
graph convolutional network /
attention mechanism
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] QIU L, KAN M, CHUA T. Modeling context in scenario template creation[C]//Proceedings of the 3rd International Joint Conference on Natural Language Processing, 2008: 157-164.
[2] ARENDARENKO E, KAKKONEN T. Ontology-based information and event extraction for business intelligence[C]//Proceedings of the 15th International Conference on Artificial Intelligence: Methodology, Systems, and Applications, 2012: 89-102.
[3] 赵妍妍,秦兵,车万翔,等.中文事件抽取技术研究[J].中文信息学报,2008,22(1): 3-8.
[4] LI Q, JI H, HUANG L. Joint event extraction via structured prediction with global features[C]//Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, 2013: 73-82.
[5] ZENG Y, FENG Y, MA R, et al. Scale up event extraction learning via automatic training data generation[C]//Proceedings of the 32nd Conference on Artificial Intelligence, 2018: 6045-6052.
[6] CHEN Y, LIU S, ZHANG X, et al. Automatically labeled data generation for large scale event extraction[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017: 409-419.
[7] NGUYEN T H, CHO K, GRISHMAN R. Joint event extraction via recurrent neural networks[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2016: 300-309.
[8] TONG M, XU B, WANG S, et al. Improving event detection via open-domain trigger knowledge[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 5887-5897.
[9] LU Y J, ZHANG H, DE BOER M, et al. Event detection with zero example: Select the right and suppress the wrong concepts[C]//Proceedings of the ACM on International Conference on Multimedia Retrieval, 2016: 127-134.
[10] 贺瑞芳,段绍杨.基于多任务学习的中文事件抽取联合模型[J].软件学报,2019,30(4): 1015-1030.
[11] LIANG X, CHENG D, YANG F, et al. F-HMTC: Detecting financial events for investment decisions based on neural hierarchical multi-label text classification[C]//Proceedings of the 29th International Joint Conference on Artificial Intelligence,2020: 4490-4496.
[12] FELDMAN R, ROSENFELD B, BAR-HAIM R, et al. The stock sonar-sentiment analysis of stocks based on a hybrid approach[C]//Proceedings of the 23rd Conference on Innovative Applications of Artificial Intelligence, 2011: 1642-1647.
[13] LI W, WONG K F, YUAN C. A design of temporal event extraction from Chinese financial news[J]. International Journal of Computer Processing of Oriental Languages, 2003, 16(01): 21-39.
[14] 万齐智,万常选,胡蓉,等.基于句法语义依存分析的中文金融事件抽取[J].计算机学报,2021,44(03): 508-530.
[15] LI Q, ZHANG Q. A unified model for financial event classification, detection and summarization[C]//Proceedings of the 29th International Conference on International Joint Conferences on Artificial Intelligence, 2021: 4668-4674.
[16] DING X, ZHANG Y, LIU T, et al. Knowledge-driven event embedding for stock prediction[C]//Proceedings of the 26th International Conference on Computational Linguistics, 2016: 2133-2142.
[17] 王雷,李瑞轩,李玉华,等.文档级无触发词事件抽取联合模型[J].计算机科学与探索,2021,15(12): 2327-2334.
[18] 仲伟峰,杨航,陈玉博,等.基于联合标注和全局推理的篇章级事件抽取[J].中文信息学报, 2019, 33(09): 88-106.
[19] YANG H, CHEN Y, LIU K, et al. DCFEE: A document-level Chinese financial event extraction system based on automatically labeled training data[C]//Proceedings of 56th Annual Meeting of the Association for Computational Linguistics, 2018: 50-55.
[20] ZHENG S, CAO W, XU W, et al. Doc2EDAG: An end-to-end document-level framework for Chinese financial event extraction[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing,2019: 337-346.
[21] YANG H, SUI D, CHEN Y, et al. Document-level event extraction via parallel prediction networks[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics,2021: 6298-6308.
[22] XU R, LIU T, LI L, et al. Document-level event extraction via heterogeneous graph-based interaction model with a tracker[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics, 2021: 3533-3546.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(1889 KB)
