面向海量新闻简报的事件演变轨迹构建方法

doi:10.3778/j.issn.1002-8331.2105-0486

摘要/Abstract

摘要： 在故事森林模型基础上提出了事件演变轨迹模型。对比故事森林模型，事件演变轨迹模型具备在涵盖不同主题和包含大量冗余信息的海量新闻简报中准确、快速提取热点事件的能力。同时，在分析和理解上下文语义的基础上，以实时在线的方式描述事件的演变过程，在不破坏已有演变结构的基础上，确保用户的浏览体验。基于32?GB的中文新闻简报数据对模型进行了评估和试点用户体验研究。结果表明，事件演变轨迹在准确识别热点事件并将新闻简报组织成符合读者阅读逻辑方面具有更强的能力。

关键词: 事件演变轨迹, 新闻简报, 热点事件, 上下文语义

Abstract: Based on the story forest model, the event evolution trajectory model is proposed. Comparing to story forest model, the event evolution trajectory model has the ability to accurately and quickly extract hot-spot events in a massive news bulletin that covers a wide range of topics and contains a wealth of redundant information. At the same time, on the basis of analyzing and understanding contextual semantics, the evolution of events is described in a real-time online manner, ensuring the user’s browsing experience without destroying the existing evolutionary structure. Finally, based on 32 GB of Chinese news bulletin data, the paper evaluates the model and pilots the user experience study. The results show that the event evolution trajectory has more ability in accurately identifying hot events and organizing news bulletins into reading logic.

Key words: event evolution trajectory, news bulletin, hot-spot event, context semantic

赵华, 邓志宏, 陈英武. 面向海量新闻简报的事件演变轨迹构建方法[J]. 计算机工程与应用, 2022, 58(24): 116-124.

ZHAO Hua, DENG Zhihong, CHEN Yingwu. Constructing Method of Events Evolution Trajectory for Massive News Bulletins[J]. Computer Engineering and Applications, 2022, 58(24): 116-124.

参考文献

[1] WANG L，CLAIRE C，GALEN M.Socially-informed timeline generation for complex events[C]//Proceedings of the 2015 Annual Conference of the North American Chapter of the ACL，Colorado，May 31-June 5，2015.Denver：ACL，2015：1055-1065.
[2] YAN R，WAN X J，JAHNA O，et al.Evolutionary timeline summarization：a balanced optimization framework via iterative substitution[C]//Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval，Beijing，July 24-28，2011：745-754.
[3] RAMESH N，FENG A，PENG F C，et al.Event threading within news topics[C]//Proceedings of the 13th ACM International Conference on Information and Knowledge Management，Washington，DC，Nov 8-13，2004：446-453.
[4] CHRISTOPHER C Y，SHI X D，WEI C P.Discovering event evolution graphs from news corpora[J].IEEE Transactions on Systems，Man，and Cybernetics-Part A：Systems and Humans，2009，39（4）：850-863.
[5] DAFNA S，CARLOS G，ERIC H.Trains of thought：generating information maps[C]//Proceedings of the 21st International Conference on World Wide Web，Lyon，April 16-20，2012：899-908.
[6] DAFNA S，YANG J W，CAROLINE S，et al.Information cartography：creating zoomable，large-scale maps of information[C]//Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，Chicago，August 11-14，2013：1097-1105.
[7] XU S Z，WANG S S，ZHANG Y.Summarizing complex events：a cross-modal solution of storylines extraction and reconstruction[C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing，Seattle，Washington，October 18-21，2013：1281-1291.
[8] LIU B，NIU D，LAI K F，et al.Growing story forest online from massive breaking news[C]//Proceedings of the 2017 ACM on Conference on Information and Knowledge Management，Singapore，Nov 6-10，2017：777-785.
[9] JACOB D，CHANG M W，KENTON L，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，June 2-7，2019.Minnesota：NAACL，2019：4171-4186.
[10] HASSAN S，LOUIQA R.A graph analytical approach for topic detection[J].ACM Transactions on Internet Technology，2013，13（2）：1-23.
[11] YAN X H，GUO J F，LAN Y Y，et al.A biterm topic model for short texts[C]//Proceedings of 22nd International Conference Companion on World Wide Web，New York，May 13，2013：1445-1456.
[12] LU Y，MEI Q，ZHAI C.Investigating task performance of probabilistic topic models：an empirical study of PLSA and LDA[J].Information Retrieval，2011，14（2）：178-203.
[13] CHANG P C，MICHEL G，CHRISTOPHER D M.Optimizing Chinese word segmentation for machine translation performance[C]//Proceedings of the Third Workshop on Statistical Machine Translation，Columbus，June，2008：224-232.
[14] RADA M，PAUL T.TextRank：bringing order into texts[C]//Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing，Barcelona，July，2004：404-411.
[15] ZHAO H，FENG Y H，CHEN Y W，et al.Weapon equipment system value analysis method based on massive text data[C]//Proceedings of the 6th International Conference on Big Data and Information Analytics，Shenzhen，Dec 4-6，2020.
[16] LI B，ZHOU H，HE J X，et al.On the sentence embeddings from pre-trained language models[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing，November 16-20，2020：9119-9130.
[17] GUAN R C，SHI X H，MARCHESE M，et al.Text clustering with seeds affinity propagation[J].IEEE Transactions on Knowledge and Data Engineering，2011，23（4）：627-637.
[18] ANDREW R，JULIA H.V-measure：a conditional entropy-based external cluster evaluation measure[C]//Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning，Prague，June，2007.Prague：ACL，2007：410-420.
[19] YANG Y M，JAIME C，RALF B，et al.Multi-strategy learning for topic detection and tracking[J].Topic Detection and Tracking，2002，12（5）：85-114.