面向新冠新闻的三阶段篇章级事件抽取方法

doi:10.3778/j.issn.1002-8331.2108-0353

摘要/Abstract

摘要： 事件抽取是信息抽取领域的一个研究热点。在新冠肺炎疫情常态化下，利用事件抽取技术可以筛选出有价值的信息。然而事件抽取领域缺乏精标注的新冠新闻训练数据集，且因部分事件的复杂性，论元不只存在于一句话中，需要多个句子才能完整描述一个事件。因此，首先构建新冠肺炎新闻数据集，接着提出一种三阶段的管道方法实现从篇章中抽取新冠肺炎事件。该方法对数据集进行事件类型分类；进行事件句的抽取；实现篇章级论元抽取。实验结果表明提出的方法能够减少事件分类时间，抽取两个事件句的条件下，对数据通报类论元识别效果最好，准确率、召回率和F1值达到75.0%、73.0%，和74.0%，证明方法能有效抽取新冠肺炎相关篇章级事件。

关键词: 新冠肺炎, 信息抽取, 事件句抽取, 篇章级事件抽取

Abstract: Event extraction is a hot research in the field of information extraction. In the face of COVID-19, event extraction technology can filter out valuable information. However, there is a lack of well-labeled news data set for COVID-19 in event extraction. Moreover, due to the complexity of some events, arguments do not only exist in one sentence, and multiple sentences are needed to fully describe an event. Therefore, an COVID-19 news events data set is constructed, and a three-stage pipeline method is proposed. It classifies event types, then it extracts event sentences. Finally, the document-level event arguments extraction is realized. The experimental results show that the model can reduce event classification time. When extracting two event sentences, the recognition effect for notification type event argument is the best. The accuracy rate, recall rate and F1 value reaches 75.0%, 73.0% and 74.0%, which proves that proposed method can effectively extract document-level COVID-19 events.

Key words: COVID-19, information extraction, event sentence extraction, document-level event extraction

郭鑫, 高彩翔, 陈千, 王素格, 王雪婧. 面向新冠新闻的三阶段篇章级事件抽取方法[J]. 计算机工程与应用, 2023, 59(3): 150-157.

GUO Xin, GAO Caixiang, CHEN Qian, WANG Suge, WANG Xuejing. Three-Stage Document-Level Event Extraction for COVID-19 News[J]. Computer Engineering and Applications, 2023, 59(3): 150-157.

参考文献

[1] ZHANG H，SONG H，WANG S，et al.A BERT-based end-to-end model for Chinese document-level event extraction[C]//Proceedings of the 19th Chinese National Conference on Computational Linguistics，2020：390-401.
[2] GUO H，WANG Z，LI P，et al.Semi-supervised method to cluster Chinese events on social streams[C]//Proceedings of the 19th Chinese National Conference on Computational Linguistics，2020：634-644.
[3] YU W，YI M，HUANG X，et al.Make it directly：event extraction based on tree-LSTM and Bi-GRU on tree-LSTM and Bi-GRU[J].IEEE Access，2020（8）：14344-14354.
[4] 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.
HE R F，DUAN S Y.Joint Chinese event extraction based on multi-task learning[J].Journal of Software，2019，30（4）：1015-1030.
[5] RILOFF E.Automatically constructing a dictionary for information extraction tasks[C]//Proceedings of the 11th National Conference on Artificial Intelligence，1993：811-816.
[6] LI P，ZHU Q，ZHOU G.Joint modeling of argument identification and role determination in Chinese event extraction with discourse-level information[C]//International Joint Conference on Artificial Intelligence，2013：2120-2126.
[7] LI Q，JI H，YU H，et al.Constructing information networks using one single model[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing，2014：1846-1851.
[8] LIU S，LIU K，HE S，et al.A probabilistic soft logic based approach to exploiting latent and global information in event classification[C]//Thirtieth AAAI Conference on Artificial Intelligence，2016：2993-2999.
[9] ZENG Y，LUO B，FENG Y，et al.WIP event detection system at TAC KBP 2016 event nugget track[C]//Proceedings of the 2016 Text Analysis Conference，2016：1-5.
[10] LIU Y，LI Q，LIU X，et al.Document information assisted event trigger detection[C]//2018 IEEE International Conference on Big Data，2018：5383-5385.
[11] WU W，ZHU X，TAO J，et al.Event detection via recurrent neural network and argument prediction[C]//CCF International Conference on Natural Language Processing and Chinese Computing，2018：235-245.
[12] CHEN Y B，YANG H，LIU K，et al.Collective event detection via a hierarchical and bias tagging networks with gated multi-level attention mechanisms[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing，2018：1267-1276.
[13] CHEN Y B，XU L，LIU K，et al.Event extraction via dynamic multi-pooling convolutional neural networks[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics，2015：167-176.
[14] FENG X，QIN B，LIU T.A language-independent neural network for event detection[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics，2016：66-71.
[15] 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，2016：300-309.
[16] MIAO J，DUAN Y X，ZHANG Y Q，et al.Method for extracting event trigger words based on the CNN-BiGRU model[J].Computer Engineering，2021，47（9）：69-74.
[17] DING L，XIANG Y.Chinese event detection with hierarchical and multi-granularity semantic fusion[J].Computer Science，2021，48（5）：202-208.
[18] WU G L，XU J N.Chinese emergency event extraction method based on named entity recognition task feedback enhancement[J].Journal of Computer Applications，2021（7）：1891-1896.
[19] HUANG E R.Peeling back the layers：detecting event role fillers in secondary contexts[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics：Human Language Technologies，2011：1137-1147.
[20] 仲伟峰，杨航，陈玉博.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（9）：88-95.
ZHONG W F，YANG H，CHEN Y B.Document-level event extraction based on joint annotation and global reasoning[J].Journal of Chinese Information Processing，2019，33（9）：88-95.
[21] YANG H，CHEN Y B，LIU K，et al.DCFEE：a document-level Chinese financial event extraction system based on automatically labeled training data[C]//Proceedings of the Association for Computational Linguistics，2018：50-55.
[22] DU X，CARDIE C.Document-level event role filler extraction using multi-granularity contextualized encoding[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics，2020：8010-8020.
[23] DIMITROV D，BARAN E，FAFALIOS P，et al.Tweets COV19-a knowledge base of semantically annotated tweets about the COVID-19 pandemic[C]//Proceedings of the 29th ACM International Conference on Information and Knowledge Management，2020：2991-2998.
[24] WANG C，LILLIS D.UCD-CS at W-NUT 2020 shared Task-3：a text to text approach for COVID-19 event extraction on social media[C]//Proceedings of the Sixth Workshop on Noisy User-Generated Text（W-NUT 2020），2020.
[25] MIHALCEA R，TARAU P.TextRank：bringing order into text[C]//Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing，2004：404-411.