Skip to main content
SpringerLink
Log in

Label graph augmented soft cascade decoding model for overlapping event extraction

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Event extraction (EE) is a fundamental information extraction task that aims to identify structured events, including event types, triggers and arguments, from unstructured texts. The overlapping EE, in which a trigger may be assigned to multiple event types, or an argument owns more than one role, is a more challenging task. Existing methods deconstruct the task in a pipeline-based cascade decoding paradigm, sequentially extracting overlapping event elements (triggers and arguments) based on the previous extracted results. On the one hand, this hard cascade decoding architecture is prone to serious error propagation in overlapping EE. On the other hand, they ignore the correlation between event types and argument roles, which is beneficial for this task. Facing these issues, we present an Event-Role label graph augmented cascade framework by modeling EE as a sub-task-dependent soft decoding architecture. To mitigate error propagation between sub-tasks, we propose a reliability-aware soft cascading module, which gradually transfers smoother features to downstream sub-tasks. To further enhance the model’s ability to classify overlapped elements, we design the Event-Role label graph representation learner to incorporate event-to-event and role-to-role association information into label space of event types and argument roles. It facilitates overlapped elements to be assigned to multiple labels with approximate feature space. We perform extensive experiments on two widely-used EE benchmark datasets, FewFC and ACE-2005, where our model outperforms state-of-the-art methods on the overlapping EE task and also adapts to the general EE without overlapped elements.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Data availability

The data that support the findings of this study are openly available in https://github.com/TimeBurningFish/FewFC and https://catalog.ldc.upenn.edu/LDC2006T06.

Notes

  1. Here, we only choose the argument roles with the overlapped argument in training set.

  2. We have converted high-order neighbors to first-order neighbors through a 3-layer GCN.

  3. If an event mention contains N events instances, we divide it into N training samples.

  4. We take same attenuation factor \(\eta\) as Trigger Extractor.

  5. In our experiments, we assign all the weights to 1.

  6. https://github.com/TimeBurningFish/FewFC.

  7. https://catalog.ldc.upenn.edu/LDC2006T06.

  8. https://github.com/JiaweiSheng/CasEE.

  9. We set the training epoch as 20 on FewFC.

References

  1. Cowie J, Lehnert W (1996) Information extraction. Commun ACM 39(1):80–91

    Article  Google Scholar 

  2. Li Q, Li J, Sheng J, Cui S, Wu J, Hei Y, Peng H, Guo S, Wang L, Beheshti A, Yu PS (2021) A Survey on Deep Learning Event Extraction: Approaches and Applications. CoRR. arXiv:2107.02126

  3. Zhang H, Liu X, Pan H, Song Y, Leung CW (2020) ASER: a large-scale eventuality knowledge graph. In: Proceedings of the 29th international world wide web conference, WWW, April 20–24, 2020, pp 201–211

  4. Du L, Ding X, Liu T, Qin B (2021) Learning event graph knowledge for abductive reasoning. In: Proceedings of the 59th annual meeting of the Association for Computational Linguistics and the 11th international joint conference on natural language processing, ACL, August 1–6, 2021, pp 5181–5190

  5. Du L, Ding X, Xiong K, Liu T, Qin B (2021) Excar: Event graph knowledge enhanced explainable causal reasoning. In: Proceedings of the 59th annual meeting of the Association for Computational Linguistics and the 11th international joint conference on natural language processing, ACL, August 1–6, 2021, pp 2354–2363

  6. Peng H, Li J, Gong Q, Song Y, Ning Y, Lai K, Yu PS (2019) Fine-grained event categorization with heterogeneous graph convolutional networks. In: Proceedings of the 28th international joint conference on artificial intelligence, IJCAI, August 10–16, 2019, pp 3238–3245

  7. Peng H, Li J, Song Y, Yang R, Ranjan R, Yu PS, He L (2021) Streaming social event detection and evolution discovery in heterogeneous information networks. ACM Trans Knowl Discov Data (TKDD) 15(5):1–33

    Article  Google Scholar 

  8. Peng H, Zhang R, Li S, Cao Y, Pan S, Yu P (2023) Reinforced, incremental and cross-lingual event detection from social messages. IEEE Trans Pattern Anal Mach Intell (TPAMI) 45(1): 980–998

  9. Ren J, Jiang L, Peng H, Liu Z, Wu J, Yu PS (2022) Evidential temporal-aware graph-based social event detection via Dempster–Shafer theory. In: International conference on web services, ICWS 2022

  10. Ren J, Peng H, Jiang L, Wu J, Tong Y, Wang L, Bai X, Wang B, Yang Q (2021) Transferring knowledge distillation for multilingual social event detection. CoRR. arXiv:2108.03084

  11. Ren J, Jiang L, Peng H, Cao Y, Wu J, Yu PS, He L (2022) From known to unknown: quality-aware self-improving graph neural network for open set social event detection. In: Proceedings of the 31th ACM international conference on information and knowledge management, CIKM 2022, Georgia, USA, October 17–21, 2022

  12. Lin X, Cao J, Zhang P, Zhou C, Li Z, Wu J, Wang B (2021) Disentangled deep multivariate Hawkes process for learning event sequences. In: IEEE international conference on data mining, ICDM 2021, Auckland, New Zealand, December 7–10, 2021, pp 360–369

  13. Deng S, Rangwala H, Ning Y (2021) Causal knowledge guided societal event forecasting. CoRR. arXiv:2112.05695

  14. Liu C, Zhou C, Wu J, Xie H, Hu Y, Guo L (2017) CPMF: a collective pairwise matrix factorization model for upcoming event recommendation. In: 2017 International joint conference on neural networks, IJCNN 2017, Anchorage, AK, USA, May 14–19, 2017, pp 1532–1539

  15. Gao L, Wu J, Qiao Z, Zhou C, Yang H, Hu Y (2016) Collaborative social group influence for event recommendation. In: Proceedings of the 25th ACM international conference on information and knowledge management, CIKM 2016, Indianapolis, IN, USA, October 24–28, 2016, pp 1941–1944

  16. Chen Y, Xu L, Liu K, Zeng D, Zhao J (2015) Event extraction via dynamic multi-pooling convolutional neural networks. In: Proceedings of the 53rd annual meeting of the Association for Computational Linguistics, ACL July 26–31, 2015, pp 167–176

  17. Sha L, Qian F, Chang B, Sui Z (2018) Jointly extracting event triggers and arguments by dependency-bridge RNN and tensor-based argument interaction. In: Proceedings of the 32th AAAI conference on artificial intelligence, AAAI, February 2–7, 2018, pp 5916–5923

  18. Chen Y, Xu L, Liu K, Zeng D, Zhao J (2015) Event extraction via dynamic multi-pooling convolutional neural networks. In: Proceedings of the 53rd annual meeting of the Association for Computational Linguistics, ACL, July 26–31, 2015, pp 167–176

  19. Sha L, Liu J, Lin C, Li S, Chang B, Sui Z (2016) RBPB: regularization-based pattern balancing method for event extraction. In: Proceedings of the 54th annual meeting of the Association for Computational Linguistics, ACL, August 7–12, 2016

  20. Yang S, Feng D, Qiao L, Kan Z, Li D (2019) Exploring pre-trained language models for event extraction and generation. In: Proceedings of the 57th conference of the Association for Computational Linguistics, ACL, July 28–August 2, 2019, pp 5284–5294

  21. Huang L, Ji H, Cho K, Dagan I, Riedel S, Voss CR (2018) Zero-shot transfer learning for event extraction. In: Proceedings of the 56th annual meeting of the Association for Computational Linguistics, ACL, July 15–20, 2018, pp 2160–2170

  22. Li F, Peng W, Chen Y, Wang Q, Pan L, Lyu Y, Zhu Y (2020) Event extraction as multi-turn question answering. In: Proceedings of the 2020 conference on empirical methods in natural language processing, EMNLP, November 16–20, 2020, pp 829–838

  23. Nguyen TH, Cho K, Grishman R (2016) Joint event extraction via recurrent neural networks. In: Proceedings of the 2016 conference of the North American chapter of the Association for Computational Linguistics, NAACL, June 12–17, 2016, pp 300–309

  24. Nguyen TM, Nguyen TH (2019) One for all: neural joint modeling of entities and events. In: Proceedings of the 33th AAAI conference on artificial intelligence, AAAI, January 27–February 1, 2019, pp 6851–6858

  25. Wadden D, Wennberg U, Luan Y, Hajishirzi H (2019) Entity, relation, and event extraction with contextualized span representations. In: Proceedings of the 2019 conference on empirical methods in natural language processing, EMNLP, November 3–7, 2019, pp 5783–5788

  26. Lu Y, Lin H, Xu J, Han X, Tang J, Li A, Sun L, Liao M, Chen S (2021) Text2event: controllable sequence-to-structure generation for end-to-end event extraction. In: Proceedings of the 59th annual meeting of the Association for Computational Linguistics ACL, August 1–6, 2021, pp 2795–2806

  27. Sheng J, Guo S, Yu B, Li Q, Hei Y, Wang L, Liu T, Xu H (2021) CasEE: a joint learning framework with cascade decoding for overlapping event extraction. In: Proceedings of the 59th conference of the Association for Computational Linguistics, ACL, August 1–6, 2021, pp 164–174

  28. Xu N, Xie H, Zhao D (2020) A novel joint framework for multiple Chinese events extraction. In: Sun M, Li S, Zhang Y, Liu Y, He S, Rao G (eds) Proceedings of the 19th Chinese computational linguistics and natural language processing, CCL, October 30–November 1, 2020, vol 12522, pp 174–183

  29. Bengio S, Vinyals O, Jaitly N, Shazeer N (2015) Scheduled sampling for sequence prediction with recurrent neural networks. In: Proceedings of the 28th annual conference on neural information processing systems, NIPS , December 7–12, 2015, pp 1171–1179

  30. Zhou Y, Chen Y, Zhao J, Wu Y, Xu J, Li J (2021) What the role is vs. what plays the role: semi-supervised event argument extraction via dual question answering. In: Proceedings of the 35th AAAI conference on artificial intelligence, AAAI, February 2–9, 2021, pp 14638–14646

  31. Doddington GR, Mitchell A, Przybocki MA, Ramshaw LA, Strassel SM, Weischedel RM (2004) The automatic content extraction (ACE) program—tasks, data, and evaluation. In: Proceedings of the 4th international conference on language resources and evaluation, LREC, May 26–28, 2004

  32. Huang R, Riloff E (2012) Modeling textual cohesion for event extraction. In: Proceedings of the 26th AAAI conference on artificial intelligence, AAAI, July 22–26, 2012

  33. Miwa M, Thompson P, Korkontzelos I, Ananiadou S (2014) Comparable study of event extraction in newswire and biomedical domains. In: Proceedings of the 25th international conference on computational linguistics, COLING, August 23–29, 2014, pp 2270–2279

  34. Chen Y, Liu S, He S, Liu K, Zhao J (2016) Event extraction via bidirectional long short-term memory tensor neural networks. In: Proceedings of the 15th Chinese computational linguistics and natural language processing, CCL, October 15–16, 2016, vol 10035, pp 190–203

  35. Venugopal D, Chen C, Gogate V, Ng V (2014) Relieving the computational bottleneck: joint inference for event extraction with high-dimensional features. In: Proceedings of the 2014 conference on empirical methods in natural language processing, EMNLP, October 25–29, 2014, pp 831–843

  36. Yang B, Mitchell TM (2016) Joint extraction of events and entities within a document context. In: Proceedings of the 2016 conference of the North American chapter of the Association for Computational Linguistics, NAACL, June 12–17, 2016, pp 289–299

  37. Luo Y, Zhao H (2020) Bipartite flat-graph network for nested named entity recognition. In: Proceedings of the 58th annual meeting of the Association for Computational Linguistics, ACL, July 5–10, 2020, pp 6408–6418

  38. Li J, Fei H, Liu J, Wu S, Zhang M, Teng C, Ji D, Li F (2022) Unified named entity recognition as word-word relation classification. Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI, February 22 - March 1, 2022, pp 10965-10973

  39. Zeng X, Zeng D, He S, Liu K, Zhao J (2018) Extracting relational facts by an end-to-end neural model with copy mechanism. In: Proceedings of the 56th annual meeting of the Association for Computational Linguistics, ACL, July 15–20, 2018, pp 506–514

  40. Wei Z, Su J, Wang Y, Tian Y, Chang Y (2020) A novel cascade binary tagging framework for relational triple extraction. In: Proceedings of the 58th annual meeting of the Association for Computational Linguistics, ACL, July 5–10, 2020, pp 1476–1488

  41. Wu Z, Pan S, Chen F, Long G, Zhang C, Yu PS (2021) A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst (TNNLS) 32(1):4–24

    Article  MathSciNet  Google Scholar 

  42. Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: Proceedings of the 5th international conference on learning representations, ICLR, April 24–26, 2017, pp 1–14

  43. Devlin J, Chang M, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the North American chapter of the Association for Computational Linguistics, NAACL, June 2–7, 2019, pp 4171–4186

  44. Liu S, Li Y, Zhang F, Yang T, Zhou X (2019) Event detection without triggers. In: Proceedings of the 2019 conference of the North American chapter of the Association for Computational Linguistics, NAACL, June 2–7, 2019, pp 735–744

  45. Yu B, Zhang Z, Sheng J, Liu T, Wang Y, Wang Y, Wang B (2021) Semi-open information extraction. In: Proceedings of the 30th international world wide web conference, WWW, April 19–23, 2021, pp 1661–1672

  46. Lafferty JD, McCallum A, Pereira FCN (2001) Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the eighteenth international conference on machine learning ICML, June 28–July 1, 2001, pp 282–289

  47. Du X, Cardie C (2020) Document-level event role filler extraction using multi-granularity contextualized encoding. In: Proceedings of the 58th annual meeting of the Association for Computational Linguistics, ACL, July 5–10, 2020, pp 8010–8020

  48. Zhang T, Ji H, Sil A (2019) Joint entity and event extraction with generative adversarial imitation learning. Data Intell 1(2):99–120

    Article  Google Scholar 

  49. Du X, Cardie C (2020) Event extraction by answering (almost) natural questions. In: Proceedings of the 2020 conference on empirical methods in natural language processing, EMNLP, November 16–20, 2020, pp 671–683

Download references

Acknowledgements

This paper is supported by the National Key R&D Program of China (2021YFB2700200), the National Natural Science Foundation of China (61772151, 62106059, U21B2021, 61932014, 61972018).

Author information

Authors and Affiliations

  1. School of Cyber Science and Technology, Beihang University, Beijing, China

    Yiming Hei & Jianwei Liu

  2. National Computer Network Emergency Response Technical Team Coordination Center of China, Beijing, 100029, China

    Lihong Wang & Shu Guo

  3. Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100080, China

    Jiawei Sheng

  4. School of Computer Science and Technology, Beihang University, Beijing, China

    Qian Li

Authors
  1. Yiming Hei
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lihong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jiawei Sheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jianwei Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Qian Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Shu Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Lihong Wang or Jiawei Sheng.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hei, Y., Wang, L., Sheng, J. et al. Label graph augmented soft cascade decoding model for overlapping event extraction. Int. J. Mach. Learn. & Cyber. 15, 79–95 (2024). https://doi.org/10.1007/s13042-022-01760-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-022-01760-y

Keywords

Search

Navigation