计算机科学 ›› 2020, Vol. 47 ›› Issue (3): 206-210.doi: 10.11896/jsjkx.190200265
张赟,李培峰,朱巧明
ZHANG Yun,LI Pei-feng,ZHU Qiao-ming
摘要： 事件可信度表示文本中事件的真实程度,描述了事件是否是一个事实,或是一种可能性,又或者是一种不可能的情况。事件可信度识别是问答系统、篇章理解等诸多相关任务的重要基础。目前,事件可信度识别的研究基本上还停留在句子级,很少涉及篇章级。因此,文中提出了一个基于门控卷积网络的篇章级事件可信度识别方法DEFI(Document-level Event Factuality Identification)。该方法首先使用门控卷积网络从句子和句法路径中抽取篇章中事件的语义和句法信息,然后通过自注意力(Self-Attention)层获取每个序列相对于自身更重要的整体信息的特征表示,从而识别出篇章级事件可信度。在中英文语料上的实验显示,与基准系统相比,DEFI的宏平均F1值和微平均F1值均得到了提高,其中在中英文语料上宏平均F1值分别提高了2.3%和4.4%,微平均F1值分别提升了2.0%和2.8%;同时,所提方法在训练速度上也提升了3倍。
中图分类号:
| [1]KLENNER M,CLEMATIDE S.How factuality determines sentiment inferences[C]∥Meeting of the Joint Conference on Lexical and Computational Semantics.2016:75-84. [2]QAZVINIAN V,ROSENGREN E,RADEV D R,et al.Rumor has it:Identifying Misinformation in Microblogs [C]∥ Meeting of the Empirical Methods in Natural Language Processing.2011:1589-1599. [3]SAURÍ R,VERHAGEN M,PUSTEJOVSKY J.Annotating and recognizing event modality in text[C]∥Meeting of the International FLAIRS.2006:333-339. [4]QIAN Z.Research on Methods of Event Factuality Identification[D].Suzhou:Soochow University,2018. [5]SAURÍ R,PUSTEJOVSKY J.FactBank:a corpus annotated with event factuality[J].Language Resources and Evaluation,2009,43(3):227-268. [6]PUSTEJOVSKY J,PATRICK H,SAURI R,et al.The time- bank corpus[C]∥Meeting of the Corpus Linguistics.2003:647-656. [7]SAURÍ R.A factuality profiler for eventualities in text[D]. Massachusetts:Brandeis University,2008. [8]CAO Y,ZHU Q M,LI P F.The Construction of Chinese Event Factuality Corpus[J].Journal of Chinese Information Proces-sing,2012,27(6):38-44. [9]VINCZE V,SZARVAS G,FARKAS R,et al.The bioscope corpus:biomedical texts annotated for uncertainty,negation and their scopes [J].Bmc Bioinformatics,2008,9(S2):S9-S9. [10]ZOU B W,ZHU Q M,ZHOU G D.Research on natural lan- guage text oriented negation and uncertainty extraction[J].Frontiers of Computer Science,2016,10(6):1039-1051. [11]SAURÍ R,PUSTEJOVSKY J.Are you sure that this happened? Assessing the factuality degree of events in text[J].Computational Linguistics,2012,38(2):1-39. [12]WERNER G,VINODKUMAR P,MONA D,et al.Committed belief tagging on the factbank and lu corpora:A comparative study[C]∥Meeting of the Second Workshop on Extra-Propositional Aspects of Meaning in Computational Semantics.2015:32-40. [13]QIAN Z,LI P F,ZHU Q M.A two-step approach for event factuality identification[C]∥Meeting of the InternationalConfe-rence on Asian Language Processing.2015:103-106. [14]QIAN Z,LI P F,ZHANG Y,et al.Event Factuality Identification via Generative Adversarial Networks with Auxiliary Classification[C]∥Meeting of the Joint Conference on Artificial Intelligence.2018:4293-4300. [15]HE T X,LI P F,ZHU Q M.Identifying Chinese event factuality with convolutional neural networks[C]∥Meeting of the Chinese Lexical Semantic Workshop.2017:284-292. [16]ZHOU X J,WAN X J,XIAO J G.Attention-based lstm network for cross-lingual sentiment classification[C]∥Meeting of the Empirical Methods in Natural Language Processing.2016:1650-1659. [17]DAUPHIN Y N,ANGELA F,MICHAEL A,et al.Language modeling with gated convolutional networks[C]∥Meeting of the Machine Learning.2017:933-941. [18]PETER S,JAKOB U,ASHISH V.Self-Attention with relative position representations[J].arXiv:1803.02155. [19]MIYATO T,MAEDA S,KOYAMA M,et al.Distributional smoothing with virtual adversarial training[J].arXiv:1507.00677. |
| [1] | 吴子仪, 李邵梅, 姜梦函, 张建朋. 基于自注意力模型的本体对齐方法 Ontology Alignment Method Based on Self-attention 计算机科学, 2022, 49(9): 215-220. https://doi.org/10.11896/jsjkx.210700190 |
| [2] | 郭雨欣, 陈秀宏. 融合BERT词嵌入表示和主题信息增强的自动摘要模型 Automatic Summarization Model Combining BERT Word Embedding Representation and Topic Information Enhancement 计算机科学, 2022, 49(6): 313-318. https://doi.org/10.11896/jsjkx.210400101 |
| [3] | 黄少滨, 孙雪薇, 李熔盛. 基于跨句上下文信息的神经网络关系分类方法 Relation Classification Method Based on Cross-sentence Contextual Information for Neural Network 计算机科学, 2022, 49(6A): 119-124. https://doi.org/10.11896/jsjkx.210600150 |
| [4] | 缪峰, 王萍, 李太勇. 基于事件动作方向的隐式因果关系抽取方法 Implicit Causality Extraction Method Based on Event Action Direction 计算机科学, 2022, 49(3): 276-280. https://doi.org/10.11896/jsjkx.211100249 |
| [5] | 肖康, 周夏冰, 王中卿, 段湘煜, 周国栋, 张民. 基于产品建模的评论问题生成研究 Review Question Generation Based on Product Profile 计算机科学, 2022, 49(2): 272-278. https://doi.org/10.11896/jsjkx.201200208 |
| [6] | 马建红, 张烔. 面向企业工程问题的专家推荐算法 Expert Recommendation Algorithm for Enterprise Engineering Problems 计算机科学, 2022, 49(1): 159-165. https://doi.org/10.11896/jsjkx.201200227 |
| [7] | 袁景凌, 丁远远, 盛德明, 李琳. 基于视觉方面注意力的图像文本情感分析模型 Image-Text Sentiment Analysis Model Based on Visual Aspect Attention 计算机科学, 2022, 49(1): 219-224. https://doi.org/10.11896/jsjkx.201000074 |
| [8] | 刘凯, 张宏军, 陈飞琼. 基于领域适应嵌入的军事命名实体识别 Name Entity Recognition for Military Based on Domain Adaptive Embedding 计算机科学, 2022, 49(1): 292-297. https://doi.org/10.11896/jsjkx.201100007 |
| [9] | 邹傲, 郝文宁, 靳大尉, 陈刚, 田媛. 基于预训练和深度哈希的大规模文本检索研究 Study on Text Retrieval Based on Pre-training and Deep Hash 计算机科学, 2021, 48(11): 300-306. https://doi.org/10.11896/jsjkx.210300266 |
| [10] | 俞亮, 魏永丰, 罗国亮, 邬昌兴. 基于知识蒸馏的隐式篇章关系识别 Knowledge Distillation Based Implicit Discourse Relation Recognition 计算机科学, 2021, 48(11): 319-326. https://doi.org/10.11896/jsjkx.201000099 |
| [11] | 李建兰, 潘岳, 李小聪, 刘子维, 王天宇. 基于CiteSpace的中文评论文本研究现状与趋势分析 Chinese Commentary Text Research Status and Trend Analysis Based on CiteSpace 计算机科学, 2021, 48(11A): 17-21. https://doi.org/10.11896/jsjkx.210300172 |
| [12] | 张明阳, 王刚, 彭起, 张岩峰. 学术论文公开评审平台数据分析 Data Analysis of OpenReview 计算机科学, 2021, 48(6): 63-70. https://doi.org/10.11896/jsjkx.200500138 |
| [13] | 史伟, 付月. 考虑语境的微博短文本挖掘:情感分析的方法 Microblog Short Text Mining Considering Context:A Method of Sentiment Analysis 计算机科学, 2021, 48(6A): 158-164. https://doi.org/10.11896/jsjkx.210200089 |
| [14] | 裴莹, 李天祥, 王鏖清, 付加胜, 韩霄松. 基于新闻的国际天然气价格趋势预测方法 Prediction Method of International Natural Gas Price Trends Based on News 计算机科学, 2021, 48(6A): 235-239. https://doi.org/10.11896/jsjkx.201000056 |
| [15] | 霍帅, 庞春江. 基于Transformer和多通道卷积神经网络的情感分析研究 Research on Sentiment Analysis Based on Transformer and Multi-channel Convolutional Neural Network 计算机科学, 2021, 48(6A): 349-356. https://doi.org/10.11896/jsjkx.200800004 |
|
||
首页