面向句义及句法的事件检测模型

事件句的句法结构有助于语义理解。针对中文领域的事件检测任务, 本文设计了面向句义及句法的事件检测模型(BDD)以增强对事件句的理解能力。以基于来自变压器的双向编码器表示 (BERT)的动态词向量为信息源, 设计基于依存树的长短时记忆网络模型(D-T-LSTM)以融合学习句法结构及上下文语义, 并加入基于依存向量的注意力机制强化对不同句法结构的区分度, 在中文突发事件语料库(CEC)上的实验证明了本文模型的有效性, 精确率、召回率、F1值均靠前, 且 F1值比基准模型提升了 5.4%, 召回率提升了 0.4%。

Abstract

The syntactic structure of event sentences contributes to semantic understanding. A novel event detection model called BERT(Bidirectional Encoder Representations from Transformers) +D (Dependency)-T(Tree)-LSTM(Long Short-Term Memory network)+D-Attention(BDD) is proposed, which aims to learn semantic and syntactic representation of sentences jointly to enhance the event-sentence understanding ability. Taking the word vector based on BERT as the information source, D-T-LSTM model is designed to integrate the learning of syntactic structure and sentence semantics. An attention mechanism based on the dependency vector is added to strengthen the distinction of different syntactic structures at the aim of event detection. Experiment results on the Chinese Emergency Corpus(CEC) prove the effectiveness of BDD. The precision, recall and F1 value of BDD are rather optimum, and the F1 value is 5.4% higher than that of the benchmark model, and the recall rate is 0.4% higher.

参考文献

[1] 高源 .中文事件抽取关键技术研究 [D].郑州:战略支援部队信息工程大学, 2015. (GAO Yuan. Research on Chinese event extraction[D]. Zhengzhou,China:Information Engineering University, 2015.)

[2] TAI Kaisheng, SOCHER R, MANNING C D. Improved semantic representations from tree-structured long short-term memory networks[C]// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Beijing:Association for Computational Linguistics, 2015:1556-1566. doi:10.3115/v1/P15-1150.

[3] LU Jiasen, YANG Jianwei, BATRA D, et al. Hierarchical co-attention for visual question answering[EB/OL]. (2016-05-31) [2021-12-29]. https://arxiv.org/abs/1606.00061v1.

[4] 张璐 .面向中文文本的事件提取方法研究 [D].北京:中国人民公安大学, 2019. (ZHANG Lu. Research on Chinese-oriented text event extraction[D]. Beijing:People's Public Security University of China, 2019.)

[5] 轩小星,廖涛,高贝贝 .中文事件触发词的自动抽取研究 [J].计算机与数字工程, 2015(3):457-461. (XUAN Xiaoxing,LIAO Tao,GAO Beibei. Automatic extraction of Chinese event trigger word[J]. Computer and Digital Engineering, 2015(3):457-461.) doi:10.3969/j.issn1672-9722.2015.03.026.

[6] LI Shen,ZHAO Zhe,HU Renfen,et al. Analogical reasoning on Chinese morphological and semantic relations[C]// Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Melbourne,Australia: Association for Computational Linguistics, 2018:138-143. doi:10.18653/v1/P18-2023.

[7] LAN Zhenzhong,CHEN Mingda,GOODMAN S,et al. ALBERT:a lite bert for self-supervised learning of language representations [EB/OL]. (2019-09-26) [2021-12-29]. https://arxiv.org/abs/1909.11942v1.

[8] SUN Yu, WANG Shuohuan, LI Yukun, et al. ERNIE 2.0: a continual pre-training framework for language understanding[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020,34(5):8968-8975. doi:10.1609/aaai.v34i05.6428.

[9] 章顺瑞 ,骆陈 .基于语义角色分析的事件抽取技术 [J].太赫兹科学与电子信息学报 , 2017,15(2):279-284. (ZHANG Shunrui, LUO Chen. Event extraction technology by semantic role analysis[J]. Journal of Terahertz Science and Electronic Information Technology, 2017,15(2):279-284.) doi:10.11805/TKYDA201702.0279.

[10] AHN D. The stages of event extraction[C]// Proceedings of the Workshop on Annotating and Reasoning about Time and Events. Sydney,Australia:Association for Computational Linguistics, 2006:1-8. doi:10.5555/1629235.1629236.

[11] LI Peifeng,ZHU Qiaoming,ZHOU Guodong. Joint modeling of argument identification and role determination in Chinese event extraction with discourse-level information[C]// Proceedings of the twenty-third international joint conference on artificial intelligence. Beijing:AAAI Press, 2013:2120-2126. doi:10.5555/2540128.2540433.

[12] CHEN Yubo, XU Liheng, LIU Kang, et al. Event extraction via dynamic multi-pooling convolutional neural networks[C]// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Beijing:Association for Computational Linguistics, 2015:167-176. doi:10.3115/v1/ P15-1017.

[13] NGUYEN T H, CHO K, GRISHMAN R. Joint event extraction via recurrent neural networks[C]// Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. San Diego,California:Association for Computational Linguistics, 2016:300-309. doi:10.18653/v1/N16-1034.

[14] LIU Shulin,LI Yang,ZHANG Feng,et al. Event detection without triggers[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Minneapolis, Minnesota: Association for Computational Linguistics, 2019:735-744. doi:10.18653/v1/N19-1080.

[15] 马晨曦 ,陈兴蜀 ,王文贤 ,等 .基于递归神经网络的中文事件检测 [J].信息网络安全 , 2018(5):75-81. (MA Chenxi,CHEN Xingshu,WANG Wenxian,et al. Chinese event detection based on recurrent neural network[J]. Netinfo Security, 2018(5):75-81.) doi:10.3969/j.issn.1671-1122.2018.05.009.

[16] 钱琳 .基于依存句法分析和深度学习的中文领域事件抽取方法研究 [D].上海 :上海财经大学 , 2020. (QIAN Lin. Research on event extraction methods in the Chinese field based on dependency syntax analysis and deep learning[D]. Shanghai, China: Shanghai University of Finance and Economics, 2020.) doi:10.27296/d.cnki.gshcu.2020.000237.

[17] 崔莹 .基于相似义原和依存句法的政外领域事件抽取方法 [J].计算机工程与科学 , 2020,42(9):1632-1639. (CUI Ying. Event extraction in political diplomacy based on similar semantics and dependency syntax[J]. Computer Engineering and Science, 2020,42(9):1632-1639.) doi:10.3969/j.issn.1007-130X.2020.09.014.

[18] 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(3):508-530. (WAN Qizhi, WAN Changxuan, HU Rong, et al. Chinese financial event extraction based on syntactic and semantic dependency parsing[J]. Chinese Journal of Computers, 2021,44(3):508-530.) doi:10.11897/SP.J.1016.2021.00508.

[19] PENNINGTON J, SOCHER R, MANNING C. Glove: global vectors for word representation[C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing(EMNLP). Doha, Qatar: Association for Computational Linguistics, 2014:1532-1543. doi:10.3115/v1/D14-1162.

[20] MIKOLOV T,CHEN Kai,CORRADO G,et al. Efficient estimation of word representations in vector space[EB/OL]. (2013-09-07)

[21] DEVLIN J,CHANG Mingwei,LEE K,et al. Bert:pre-training of deep bidirectional transformers for language understanding[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Minneapolis,Minnesota:Association for Computational Linguistics, 2019:4171-4186. doi:10.18653/v1/ N19-1423.

[22] GóMEZ-RODRíGUEZ C, ALONSO-ALONSO I, VILARES D. How important is syntactic parsing accuracy? An empirical evaluation on rule-based sentiment analysis[J]. Artificial Intelligence Review, 2019, 52(3): 2081-2097. doi: 10.1007/s10462- 017-9584-0.

[23] 刘挺 ,车万翔 ,李正华 .语言技术平台 [J].中文信息学报 , 2011,25(6):53-62. (LIU Ting,CHE Wanxiang,LI Zhenghua. Language technology platform[J]. Journal of Chinese Information Processing, 2011, 25(6): 53-62.) doi: 10.3969/j. issn. 1003-0077.2011. 06.008.

[24] SOCHER R, LIN C C Y, NG A Y, et al. Parsing natural scenes and natural language with recursive neural networks[C]// Proceedings of the 28th International Conference on International Conference on Machine Learning. Bellevue,Washington,USA: Omnipress, 2011:129-136. doi:10.5555/3104482.3104499.

[25] ZAREMBA W,SUTSKEVER I. Learning to execute[EB/OL]. (2014-10-17) [2021-12-29]. https://arxiv.org/abs/1410.4615v1.

柏瑶, 刘丹, 郭又铭, 李美文. 面向句义及句法的事件检测模型[J]. 太赫兹科学与电子信息学报, 2023, 21(12): 1464. BAI Yao, LIU Dan, GUO Youming, LI Meiwen. Event detection with joint learning of semantic and syntactic representation[J]. Journal of terahertz science and electronic information technology, 2023, 21(12): 1464.

面向句义及句法的事件检测模型

关于本站 Cookie 的使用提示

全站搜索

面向句义及句法的事件检测模型

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索