文本中事件因果关系识别与应用技术综述

李顺航,周刚,卢记仓,李志博,黄宁博,陈静

PDF(6475 KB)
PDF(6475 KB)
中文信息学报 ›› 2024, Vol. 38 ›› Issue (9) : 1-23.
综述

文本中事件因果关系识别与应用技术综述

  • 李顺航1,2,周刚1,2,卢记仓1,2,李志博1,2,黄宁博1,2,陈静1,2
作者信息 +

A Survey on Event Causality Identification and Applications in Texts

  • LI Shunhang1,2, ZHOU Gang1,2, LU Jicang1,2, LI Zhibo1,2, HUANG Ningbo1,2, CHEN Jing1,2
Author information +
History +

摘要

事件因果关系是一类重要的逻辑关系,其揭示了事件发展的动因与规律。通过自然语言处理技术对事件之间蕴含的因果关系进行识别,能够帮助形成事件因果知识库,进而促进诸如事件预测、智能问答等下游任务性能提升与可解释性增强,具有重要理论与实践价值。基于此,该文围绕事件因果关系识别与应用展开综述。首先,介绍文本中事件因果关系、因果关系识别等基本概念与任务定义,明确研究范畴;随后,总结归纳因果关系识别任务常用数据集与评测指标,并对典型评测数据集进行探索分析,进而充分挖掘任务固有难点;然后,按照基于规则挖掘、基于特征工程和基于深度学习三个类别对因果关系识别相关模型与方法进行划分,并给出系统阐释、对比和总结,并对事件因果关系支撑的下游应用场景与方法进行了概述,进一步说明了事件因果关系的重要应用价值;最后,针对文本中事件因果关系识别任务的现有挑战和未来技术方向进行了讨论与展望。

Abstract

Causality is an important type of logical relation between events that expresses high-level logical information and reveals event development patterns. The identification of event causality contained in texts via natural language processing methods is important in providing interpretability and robustness for various downstream applications such as question answering and event prediction. Therefore, we comprehensively review both the identification and application of event causality. First, to clarify the research scope, the basic concept of causality and the task definition of event causality identification (ECI) are introduced. Then, common-used datasets for ECI are summarized and further explored to figure out the inherent difficulties. Subsequently, following the technology development timeline, related ECI methods fall into three categories: rule mining, feature engineering, and deep learning. Based on this, a systematic and structured introduction, comparison, and summary are provided. Moreover, a brief overview of the application scenario of event causality is given to further show the significant application value of causal knowledge. Finally, the existing challenges and future research directions on ECI are discussed.

关键词

因果关系识别 / 自然语言处理 / 深度学习 / 数据增强 / 知识提升

Key words

event causality identification / natural language processing / deep learning / data augmentation / knowledge enhancement

引用本文

EndNote

Ris (Procite)

Bibtex

导出引用
李顺航,周刚,卢记仓,李志博,黄宁博,陈静. 文本中事件因果关系识别与应用技术综述. 中文信息学报. 2024, 38(9): 1-23
LI Shunhang, ZHOU Gang, LU Jicang, LI Zhibo, HUANG Ningbo, CHEN Jing. A Survey on Event Causality Identification and Applications in Texts. Journal of Chinese Information Processing. 2024, 38(9): 1-23

参考文献

[1] ETMINAN M, COLLINS G S, MANSOURNIA M A. Usingcausal diagrams to improve the design and interpretation of medical research[J]. Chest, 2020, 158(1): S21-S28.
[2] LEE B. Causal relationsamong stock returns, interest rates, real activity, and inflation[J]. Journal of Finance, 1992, 47(4): 1591-1603.
[3] GOPNIK A, SCHULZ L. Causal learning: Psychology, philosophy, and computation[M/OL]. Oxford: Oxford University Press, 2007. https://academic.oup.com/book/36085[2023-06-19].
[4] 李家宁, 熊睿彬, 兰艳艳, 等. 因果机器学习的前沿进展综述[J]. 计算机研究与发展, 2023, 60(1): 59-84.
[5] 李超, 求文星. 基于机器学习的因果推断方法研究进展[J]. 统计与决策, 2021, 11: 10-15.
[6] 陈越, 何宇豪, 孙亚伟, 等. 基于抽象事理图谱的因果简答题求解方法[J]. 中文信息学报, 2022, 36(4): 124-136.
[7] GUO R, CHENG L, LI J, et al. A survey of learning causality with data: Problems and methods[J]. ACM Computing Surveys, 2020, 53(4): 1-37.
[8] RESNICK C, LITANY O, KAR A, et al. Causal BERT: Improving object detection by searching for challenging groups[C]//Proceedings of the International Conference on Computer Vision, 2021: 2972-2981.
[9] ZHANG C TIAN Z, ZHU J, et al. C-CAM: Causal CAM for weakly supervised semantic segmentation on medical image[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 11676-11685.
[10] DENG S, RANGWALA H, NING Y. Causal knowledge guided societal event forecasting[J]. arXiv preprint arXiv:2112.05695, 2021.
[11] YANG J, HAN S, POON J. A survey on extraction of causal relations from natural language text[J]. Knowledge and Information Systems, 2022, 64(5):1161-1186.
[12] 王朱君, 王石, 李雪晴, 等. 基于深度学习的事件因果关系抽取综述[J]. 计算机应用, 2021, 41(05):1247-1255.
[13] LIU Y, TIAN J, ZHANG L, et al. A survey on event relation identification[C]//Proceedings of China Conference on Knowledge Graph and Semantic Computing, 2020: 173-184.
[14] HAN M, WANG Y. A survey on the identification of causal relation in texts[C]//Proceedings of the IEEE International Conference on Progress in Informatics and Computing, 2021: 1-7.
[15] DRURY B, GONCALO O H, De A L. A survey ofthe extraction and applications of causal relations[J]. Natural Language Engineering, 2022, 28(3):361-400.
[16] HEINDORF S, SCHOLTEN Y, WACHSMUTH H, et al. CauseNet: Towards a causality graph extracted from the web[C]//Proceedings of the 29th ACM InternationalConference on Information & Knowledge Management, 2020: 3023-3030.
[17] 李金妹, 李福印, Alan Cienki. 初始/持续因果关系的理论研究及其最新进展[J]. 西安外国语大学学报, 2020, 28(04):17-22.
[18] 文凤. 因果关系的表达与逻辑推理[D]. 北京:首都师范大学硕士学位论文, 2004.
[19] 陈秋雅. 基于构式语法的因果连词because研究[D]. 武汉:中南财经政法大学硕士学位论文, 2017.
[20] 吴吉东, 刘馨蔓. 基于入场理论的汉英因果复句认知工作机制研究[J]. 解放军外国语学院学报, 2021, 44(06):57-64,126.
[21] PEARL J. Causal inference in statistics: An overview[J]. Statistics Surveys, 2009, 3:96-146.
[22] 李冬梅, 张扬, 李东远, 等. 实体关系抽取方法研究综述[J]. 计算机研究与发展, 2020, 57(7): 1424-1448.
[23] 杨雪蓉, 洪宇, 陈亚东, 等. 事件关系检测的任务体系概述[J]. 中文信息学报, 2015, 29(4):25-32.
[24] 赵妍妍, 秦兵, 车万翔, 等. 中文事件抽取技术研究[J]. 中文信息学报, 2008, 22(1): 3-8.
[25] GIRJU R, NAKOV P, NASTASE V, et al. SemEval task 04: Classification of semantic relations between nominals[C]//Proceedings of the4th International Workshop on Semantic Evaluations, 2007: 13-18.
[26] HENDRICKX I, Kim S N, KOZAREVA Z, et al. SemEval-2010 task 8: Multi-way classification of semantic relations between pairs of nominals[C]//Proceedings of the 5th International Workshop on Semantic Evaluation, 2009: 33-38.
[27] YANG X, OBADINMA S, ZHAO H, et al. SemEval-2020 Task 5: Counterfactual recognition[C]// Proceedings of the 14th Workshop on Semantic Evaluation, 2020: 322-335.
[28] MARIKO D, ABI AKL H, LABIDURIE E, et al. Financialdocument causality detection shared task[J]. arXiv preprint arXiv :2012.02505, 2020.
[29] GORDON A, KOZAREVA Z, ROEMMELE M. SemEval Task 7: Choice of plausible alternatives: an evaluation of commonsense causal reasoning[C]//Proceedings of the 6th International Workshop on Semantic Evaluation, 2012: 394-398.
[30] TANDON N, DALVI B, SAKAGUCHI K, et al. WIQA: A dataset for “What if...” reasoning over procedural text[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 6076-6085.
[31] CASELLI T, VOSSEN P. The event storyLine corpus: A new benchmark for causal and temporal relation extraction[C]//Proceedings of the Events and Stories in the News Workshop, 2017: 77-86.
[32] DUNIETZ J, LEVIN L, CARBONELL J. The BECauSE Corpus 2.0: Annotating causality and overlapping relations[C]//Proceedings of the 11th Linguistic Annotation Workshop, 2017: 95-104.
[33] MIRZAL P, TONELLI S. Ananalysis of causality between events and its relation to temporal information[C]// Proceedings of the 25th International Conference on Computational Linguistics: Technical Papers, 2014: 2097-2106.
[34] KYRIAKAKIS M, ANDROUTSOPOULOS I, SAUDABAYEV A, et al. Transfer learning for causal sentence detection[C]//Proceedings of the 18th BioNLP Workshop and Shared Task, 2019: 292-297.
[35] GARCIA D. COATIS, an NLP system to locate expressions of actions connected by causality links[C]// Proceedings of International Conference on Knowledge Engineering and Knowledge Management, 1997: 347-352.
[36] KHOO C S G, KORNF J, ODDY R N, et al. Automatic extraction of cause-effect information from newspaper text without knowledge-based inferencing[J]. Literary and Linguistic Computing, 1998,13(4):177-18.
[37] GIRJU R. Automatic detection of causal relations for question answering[C]//Proceedings of the ACL Workshop on Multilingual Summarization and Question Answering, 2003: 76-83.
[38] GEORGEA M. WordNet: A lexical database for English[J]. Commun. ACM, 1995,38(11): 39-41.
[39] KHOO C S G, CHAN S, NIU Y. Extractingcausal knowledge from a medical database using graphical patterns[C]//Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics, 2000: 336-343.
[40] BEAMER B, GIRJU R. Using a bigram event model to predict causal potential[C]//Proceedings of International Conference on Intelligent Text Processing and Computational Linguistics, 2009: 430-441.
[41] DO Q, CHAN Y, ROTH D. Minimally supervised event causality identification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2011: 294-303.
[42] LUO Z, SHA Y, ZHU K, et al. Commonsensecausal reasoning between short texts[C]//Proceedings of 15th International Conference on Principles of Knowledge Representation and Reasoning, 2016: 421-430.
[43] BEAMER B, ROZOVSKAYA A, GIRJU R. Automatic semantic relation extraction with multiple boundary generation[C]//Proceedings of the 23rd AAAI Conference on Artificial Intelligence, 2008: 824-829.
[44] GIRJU R, BEAMER B, ROZOVSKAYA A, et al. A knowledge-rich approach to identifying semantic relations between nominals[J]. Information Processing & Management, 2010, 46(5): 589-610.
[45] BLANCO E, CASTELL N, MOLDOVAN D. Causalrelation extraction[C]//Proceedings of the 6th International Conference on Language Resources and Evaluation, 2008: 310-313.
[46] ZHAO S, LIU T, ZHAO S, et al. Event causality extraction based on connectives analysis[J]. Neurocomputing, 2016,173(3):1943-1950.
[47] GAO L, CHOUBEY P K, HUANG R. Modeling document-level causal structures for event causal relation identification[C]// Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019: 1808-1817.
[48] PITLER E, LOUIS A, NENKOVA A. Automatic sense prediction for implicit discourse relations in text[C]// Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conf on Natural Language Processing of the AFNLP, 2009: 683-691.
[49] SORGENTE A, VETTIGLI G, MELE F. Automatic extraction of cause-effect relations in natural language text[J]. DART@ AI* IA, 2013: 37-48.
[50] SOCHER R, HUVAL B, MANNING C D, et al. Semantic compositionality through recursive matrix-vector spaces[C]//Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, 2012: 1201-1211.
[51] HASHIMOTO K, MIWA M, TSURUOKA Y, et al. Simple customization of recursive neural networks for semantic relation classification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2013: 1372-1376.
[52] DASGUPTA T, SAHA R, DEY L, et al. Automatic extraction of causal relations from text using linguistically informed deep neural networks[C]//Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, 2018: 306-316.
[53] XU Y, MOU L, LI G, et al. Classifying relations via long short term memory networks along shortest dependency paths[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2015:1785-1794.
[54] YANG Z, LIU W, LIU Z. Event causality identification by modeling events and relation embedding[C]//Proceedings of the International Conference on Neural Information Processing, 2018: 59-68.
[55] LI Z, LI Q, ZOU X, et al. Causality extraction based on self-attentive BiLSTM-CRF with transferredembeddings[J]. Neurocomputing, 2021, 423: 207-219.
[56] KRUENGKRAI C, TORISAWA K, HASHIMOTO C, et al. Improving event causality recognition with multiple background knowledge sources using multi-column convolutional neural networks[C]// Proceedings of 31st AAAI Conference on Artificial Intelligence, 2017: 3466-3473.
[57] LI P, MAO K. Knowledge-oriented convolutional neural network for causal relation extraction from natural language texts[J]. Expert Systems with Applications, 2019,115: 512-523.
[58] 陈雨龙, 付乾坤, 张岳. 图神经网络在自然语言处理中的应用[J]. 中文信息学报, 2021, 35(3): 1-23.
[59] ZHAO K, JI D, HE F, et al. Document-level event causality identification via graph inference mechanism[J]. Information Sciences, 2021, 561: 115-129.
[60] DEVLIN J, CHANG M, LEE K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics, 2019: 4171-4186.
[61] CHEN M, CAO Y, DENG K, et al. ERGO: Event relational graph transformer for document-level event causality identification[C]//Proceedings of the 29th International Conference on Computational Linguistics. Gyeongju, International Committee on Computational Linguistics, 2022: 2118-2128.
[62] BELTAGY L, MATTHEW E P, ARMAN C. Longformer: The long-document transformer[J]. arXiv preprint arXiv: 2004.05150, 2020.
[63] TRAN P M, NGUYEN T H. Graph convolutional networks for event causality identification with rich document-level structures[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021: 3480-3490.
[64] TAN F A, NG S K. NUS-IDS at FinCausal: Dependencytree in graph neural network for better cause-effect span detection[C]//Proceedings of the 3rd Financial Narrative Processing Workshop, 2021: 37-43.
[65] GAO J, LUO X, WANG H. Chinese causal event extraction using causality-associated graph neural network[J]. Concurrency and Computation: Practice and Experience, 2022,34(3): 135-148.
[66] WU S, HE Y. Enriching pre-trained language model with entity information for relation classification[C]// Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2019: 2361-2364.
[67] MATTHEW E P, MARK N, MOHIT I, et al. Deep contextualized word representations[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018: 2227-2237.
[68] HOSSEINI P, BRONIATOWSKI D A, DIAB M. Predicting directionality in causal relations in text[J]. arXivpreprint arXiv:2103.13606, 2021.
[69] MANDAR J, CHEN D, LIU Y, et al. SpanBERT: Improving pre-training by representing and predicting spans[C]//Proceedings of Transactions of the Association for Computational Linguistics, 2020: 64-77.
[70] RADFORD A, WU J, CHILD R, et al. Language models are unsupervised multitask learners[J]. OpenAIBlog, 2019, 1(8):1-9.
[71] COLIN R, NOAM S, ADAM R, et al. Exploring the limits of transfer learning with a unified text-to-text transformer[J]. The Journal of Machine Learning Research, 2020, 21(1): 5485-5551.
[72] MAN H, NGUYEN M, NGUYEN T. Event causality identification via generation of important context words[C]//Proceedings of the 11th Joint Conference on Lexical and Computational Semantics, 2022: 323-330.
[73] LI Z, DING X, LIU T, et al. Guided generation of cause and effect[C]//Proceedings of the 29th International Joint Conference on Artificial Intelligence, 2020: 3629-3636.
[74] KHETAN V, RAMNANI R, ANAND M, et al. Causal BERT: Language models for causality detection between events expressed in text[J]. arXiv preprint arXiv:2012.05453, 2021.
[75] HOSSEINI P, BRONIATOWSKIDA, DIAB M. Knowledge-Augmented Language Models for Cause-Effect Relation Classification[C]//Proceedings of the 1st Workshop on Commonsense Representation and Reasoning, 2022: 43-48.
[76] HWANG J D, BHAGAVATULA C, LE B R, et al. Atomic 2020: On symbolic and neural commonsense knowledge graphs[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2021: 6384-6392.
[77] MOSTAFAZADEH N, KALYANPUR A, MOON L, et al. GLUCOSE: GeneraLized and contextualized story explanations[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2020: 4569-4586.
[78] LI S, LI X, SHANG L, et al. How pre-trained language models capture factual knowledge? A causal-inspired analysis[C]//Proceedings of the Association for Computational Linguistics, 2022: 1720-1732.
[79] BAYER M, KAUFHOLD M A, REUTER C. Asurvey on data augmentation for text classification[J]. ACM Computing Surveys, 2022,55(7):1-39.
[80] ZUO X, CHEN Y, LIU K, et al. KnowDis: Knowledge enhanced data augmentationfor event causality detection via distant supervision[C]//Proceedings of the 28th International Conference on Computational Linguistics, 2020: 1544-1550.
[81] ZUO X, CAOP, CHEN Y, et al. LearnDA: Learnable knowledge-guided data augmentation for event causality identification[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021: 3558-3571.
[82] STALINAITE· I, GORINSKI P J, IACOBACCI I. Improving commonsense causal reasoning by adversarial training and data augmentation[C]//Proceedings of the 35th AAAI Conference on Artificial Intelligence, 2021: 13834-13842.
[83] PRASAD R, DINESH N, LEE A, et al. The Penn Discourse TreeBank 2.0.[C]//Proceedings of the 6th International Conference on Language Resources and Evaluation, 2008: 2961-2968.
[84] SPEER R, CHIN J, HAVASI C. ConceptNet 5.5: Anopen multilingual graph of general knowledge[C]// Proceedings of the AAAI Conference on Artificial Intelligence, 2017: 4444-4451.
[85] BAKER C F, FILLMORE C J, LOWE J B. The Berkeley FrameNet Project[C]//Proceedings of 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, 1998: 86-90.
[86] RIEDEL S, YAO L, MCCALLUM A. Modeling relations and their mentions without labeled text[C]//Proceedings of Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 2010: 148-163.
[87] LIU J, CHEN Y, ZHAO J. Knowledge enhanced event causality identification with mention masking generalizations[C]//Proceedings of the 29th International Joint Conference on Artificial Intelligence, 2020: 3608-3614.
[88] CAO P, ZUO X, CHEN Y, et al. Knowledge-enriched event causality identification via latent structureinduction networks[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021: 4862-4872.
[89] ZHAO Z, HANG Y, LUO X, et al. IA-ICGCN: Integratingprior knowledge via intra-event association and inter-event causality for Chinese causal event extraction[C]//Proceedings of International Conference on Artificial Neural Networks, 2022: 519-531.
[90] DU L, DING X, XIONG K et al. ExCAR: Event graph knowledge enhanced explainable causal reasoning[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021: 2354-2363.
[91] ZUO X, CAO P, CHEN Y, et al. Improving event causality identification via self-supervised representation learning on external causal statement[C]//Proceedings of the Association for Computational Linguistics, 2021: 2162-2172.
[92] ZHAO L. Event prediction in the big data era: a systematic survey[J]. ACM Computing Surveys, 2021, 54(5): 1-37.
[93] LIU Z, ZHU Z, JING G, et al. Forecast methods for time series data: A survey[J]. IEEE Access, 2021, 9: 91896-91912.
[94] RADINSKY K, DAVIDOVICH S, MARKOVITCH S. Learning causality for news events prediction[C]// Proceedings of the 21st Int Conf on World Wide Web. New York: Association for Computing Machinery, 2012. 909-918.
[95] BIZER C, HEATH T, BERNERS-LEE T. Linked data-the story so far[J]. International Journal on Semantic Web and Information Systems Semantic Web, 2009,5:1-22.
[96] SHRESTHA P,LEE B S, BAGROW J P. Predicting an effect event from a new cause event using a semantic web based abstraction tree of past cause-effect event pairs[J]. SIMBig, 2017: 1-10.
[97] ZHAO S, WANG Q, MASSUNG S, et al. Constructing and embedding abstract event causality networks from text snippets[C]//Proceedings of the 10th ACM International Conference on Web Search and Data Mining, 2017: 335-344.
[98] DALAL D, ARCAN M, BUITELAAR P. Enhancing multiple-choice question answering with causal knowledge[C]//Proceedings of Deep Learning Inside Out: The 2nd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, 2021: 70-80.
[99] ZHANG M, ZHANG R, LI Y, et al. Crake: Causal-enhanced table-filler for question answering over large scale knowledge base[C]//Proceedings of the Association for Computational Linguistics, 2022: 1787-1798.
[100] OH J H, TORISAWA K, KRUENGKRAI C, et al. Multi-column convolutional neural networks with causality-attention for why-question answering[C]//Proceedings of the 10th ACM International Conference on Web Search and Data Mining, 2017: 415-424.
[101] HIGASHINAKA R, ISOZAKI H. Automatically acquiring causal expression patterns from relation-annotated corpora to improve question answering for why-questions[J]. ACM Transactions on Asian Language Information Processing, 2008, 7(2): 1-29.
[102] OH J-H, TORISAWA K, HASHIMOTO C, et al. A semi-supervised learning approach to why-question answering[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2016: 3022-3029.
[103] 胡晗, 刘鹏远. 小样本关系分类研究综述[J]. 中文信息学报, 2022, 36(2): 1-11.

基金

河南省科技攻关计划项目(222102210081);河南省自然科学基金(222300420590)
PDF(6475 KB)

531

Accesses

0

Citation

Detail
段落导航
相关文章

  • 版权所有 © 《中文信息学报》编辑部 网站统计

    地址：北京市海淀区中关村南四街4号　邮编：100190　电话：010-62562916　E-mail：cips@iscas.ac.cn

    本系统由北京玛格泰克科技发展有限公司设计开发

/

〈 〉