案件要素异构图的舆情新闻抽取式摘要

doi:10.3778/j.issn.1002-8331.2108-0358

摘要/Abstract

摘要： 案件舆情摘要是指从与司法案件相关的舆情信息中抽取与案件相关的句子作为摘要。在案件舆情文本中通常包含如涉案人员、案发地点等案件要素，这些案件要素对于摘要生成有着重要的指导意义。因此，针对案件舆情文本的特点，提出一种基于案件要素异构图的抽取式摘要模型。首先通过基于图注意力机制融入案件要素的方法，构建一个由句子节点、词节点和案件要素节点组成的异构图，来捕捉句子间的关联关系，最后对句子进行分类，生成摘要。在基于百度百科构建的案件舆情数据集上进行实验，结果表明，模型相比基于注意力机制融入案件要素的方法在ROUGE-L上取得14.22个百分点的提升。

关键词: 案件舆情摘要, 案件要素, 图注意力机制, 异构图

Abstract: Case public opinion summary refers to extracting sentences related to the case as a summary from the public opinion information related to judicial cases. The public opinion text of the case usually contains case elements such as the person involved and the location of the case, these case elements have important guiding significance for abstract generation. Therefore, in view of the characteristics of the case public opinion text, an extractive summary model based on the heterogeneous graph of case elements is proposed. Firstly, a heterogeneous graph composed of sentence nodes, word nodes and case element nodes is constructed by integrating the case elements based on the graph attention mechanism, to capture the relationship between sentences. Finally, the sentences are classified to generate a summary. Experiment on the case public opinion data set based on Baidu Encyclopedia, the results show that the model in this paper achieves 14.22 percentage points improvement in ROUGE-L compared to the method of incorporating case element based on the attention mechanism.

Key words: case public opinion summary, case elements, graph attention mechanism, heterogeneous graph

李刚, 余正涛, 黄于欣. 案件要素异构图的舆情新闻抽取式摘要[J]. 计算机工程与应用, 2023, 59(4): 112-119.

LI Gang, YU Zhengtao, HUANG Yuxin. Extractive Summary for Public Opinion News via Case Elements Heterogeneous Graph[J]. Computer Engineering and Applications, 2023, 59(4): 112-119.

参考文献

[1] 刘娜，路莹，唐晓君，等.基于LDA重要主题的多文档自动摘要算法[J].计算机科学与探索，2015，9（2）：242-248.
LIU N，LU Y，TANG X J，et al.Multi-document summarization algorithm based on significance topic of LDA[J].Journal of Frontier of Computer Science and Technology，2015，9（2）：242-248.
[2] 吴仁守，刘凯，王红玲.一种基于局部—全局主题关系的演化式摘要系统[J].中文信息学报，2018，32（9）：75-83.
WU R S，LIU K，WANG H L.An evolutionary summarization system based on local-global topic relationship[J].Journal of Chinese Information Processing，2018，32（9）：75-83.
[3] 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.
[4] NALLAPATI R，ZHAI F，ZHOU B.SummaRuNNer：a recurrent neural network based sequence model for extractive summarization of documents[C]//Proceedings of the 31st AAAI Conference on Artificial Intelligence，California，Feb 4-9，2017.Menlo Park：AAAI，2017：3075-3081.
[5] ZHANG X X，LAPATA M，WEI F R，et al.Neural latent extractive document summarization[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing，Brussels，Oct 31-Nov 4，2018.Stroudsburg：ACL，2018：779-784.
[6] 韩鹏宇，高盛祥，余正涛，等.基于案件要素指导的涉案舆情新闻文本摘要方法[J].中文信息学报，2020，34（5）：56-63.
HAN P Y，GAO S X，YU Z T，et al.Case-involved public opinion news summarization with case elements guidance[J].Journal of Chinese Information Processing，2020，34（5）：56-63.
[7] HU L M，YANG T C，SHI C，et al.Heterogeneous graph attention networks for semi-supervised short text classification[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing，2019：4823-4832.
[8] TU M，WANG G T，HUANG J，et al.Multi-hop reading comprehension across multiple documents by reasoning over heterogeneous graphs[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics，Florence.Stroudsburg：ACL，2019：2704-2713.
[9] TAN J，WAN X，XIAO J.Abstractive document summarization with a graph-based attentional neural model[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics，Vancouver.Stroudsburg：ACL，2017：1171-1181.
[10] LIU Y，LAPATA M.Text summarization with pretrained encoders[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing，2019：3721-3731.
[11] DEVLIN J，CHANG M W，LEE K.BERT：pre-training of deep bidirectional transformers for language understanding[J].arXiv：1810.04805，2018.
[12] ZHONG M，LIU P F，CHEN Y R，et al.Extractive summarization as text matching[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.Stroudsburg：ACL，2020.
[13] LECUN Y，BOTTOU L，BENGIO Y，et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE，1998，86（11）：2278-2324.
[14] HOCHREITER S，SCHMIDHUBER J.Long short-term memory[J].Neural Computation，1997，9（8）：1735-1780.
[15] PETAR V，CUCURULL G，CASANOVA A.Graph attention networks[J].arXiv：1710.10903，2017.
[16] WANG C H，ZHANG M，MA S P，et al.Automatic online news issue construction in web environment[C]//Proceedings of the 17th International Conference on World Wide Web，2008：457-466.
[17] LIN C Y.ROUGE：a package for automatic evaluation of summaries[C]//Workshop on Text Summarization Branches Out，Post-Conference Workshop of ACL 2004，2004：74-81.
[18] CARBONELL J，GOLDSTEIN J.The use of MMR，diversity-based reranking for reordering documents and producing summaries[C]//Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval，1998：335-336.
[19] VASWANI A，SHAZEER N，PARMAR N.Attention is all you need[C]//Advances in Neural Information Processing Systems，2017：5998-6008.