Skip to main content
SpringerLink
Log in

Event detection from text using path-aware graph convolutional network

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Event detection aims to detect events from text by locating event triggers and classifying them into predefined event types. Current state-of-the-art event detection methods benefit from integration of syntactic dependency into graph convolutional network (GCN). Despite the great success of GCN-based event detection methods, there are still two problems. Firstly, most GCN-based methods are designed as stacked structure to capture high-order contextual information, which will result in over-smoothing problem; secondly, dependency type information are not fully utilized in current GCN-based methods due to severe sparsity problem of some dependency types. In this paper, we propose P ath-Aware G raph C onvolutional N etwork (PGCN) model, shedding lights on simultaneously tackling these two problems. Specifically, PGCN is designed as flat structure to avoid over-smoothing problem, while path-aware aggregation is proposed to capture all-order contextual information and integrate dependency type information into feature space at the same time. Moreover, to deal with sparsity problem of some path types, we further adopt latent factor decomposition (LFD) technique by sharing parameters among different kinds of path. Our method is verified on the benchmark ACE 2005 English dataset. Experimental results show that our method gets 1.4% improvement on F1 score over state-of-the-art method, and performs more stably than other GCN-based methods with separate random initializations.

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

Similar content being viewed by others

Notes

  1. Here we use ‘path’ throughout this paper to refer to single dependency edge (with direction and dependency type) or multiple connected edge between two words in dependency tree.

  2. http://nlp.stanford.edu/software/stanford-englishcorenlp-2018-10-05-models.jar

  3. For each combination of K and L, its maximum order is calculated as K × L

References

  1. Fourth Message Uunderstanding Conference (MUC-4) (1992) Proceedings of a conference held in McLean, Virginia. https://www.aclweb.org/anthology/M92-1000

  2. Nguyen T H, Grishman R (2018) Graph convolutional networks with argument-aware pooling for event detection. In: National Conference on Artificial Intelligence, pp 5900–5907

  3. Liu X, Luo Z, Huang H (2018) Jointly multiple events extraction via attention-based graph information aggregation. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, pp 1247–1256

  4. Yan H, Jin X, Meng X, Guo J, Cheng X (2019) Event detection with multi-order graph convolution and aggregated attention. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, Hong Kong, pp 5765–5769

  5. Cui S, Yu B, Liu T, Zhang Z, Wang X, Shi J (November 2020) Edge-enhanced graph convolution networks for event detection with syntactic relation. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. https://www.aclweb.org/anthology/2020.findings-emnlp.211. Association for Computational Linguistics, Online, pp 2329–2339

  6. Li L, Jin L, Zhang Z, Liu Q, Sun X, Wang H (2020) Graph convolution over multiple latent context-aware graph structures for event detection. IEEE Access 8:171435–171446. https://doi.org/10.1109/ACCESS.2020.3024872

    Article  Google Scholar 

  7. 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 and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp 167–176

  8. Nguyen T H, Grishman R (2015) Event detection and domain adaptation with convolutional neural networks. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pp 365–371

  9. Jenatton R, Roux N L, Bordes A, Obozinski G (2012) A latent factor model for highly multi-relational data. In: International Conference on Neural Information Processing Systems

  10. Ji H, Grishman R (June 2008) Refining event extraction through cross-document inference. In: Proceedings of the 2008 Association for Computational Linguistics. Association for Computational Linguistics, Columbus, pp 254–262

  11. Cao K, Li X, Fan M, Grishman R (2015) Improving event detection with active learning. In: Proceedings of the International Conference Recent Advances in Natural Language Processing. INCOMA Ltd. Shoumen, Hissar, pp 72–77

  12. Cao K, Li X, Grishman R (2015) Improving event detection with dependency regularization. In: Proceedings of Recent Advances in Natural Language Processing, pp 78–83

  13. Ahn D (2006) The stages of event extraction. In: Proceedings of the Workshop on Annotating and Reasoning about Time and Events. ARTE ’06. Association for Computational Linguistics, USA, pp 1–8

  14. Patwardhan S, Riloff E (2009) A unified model of phrasal and sentential evidence for information extraction. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Singapore, pp 151–160

  15. Liao S, Grishman R (2010) Using document level cross-event inference to improve event extraction. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Uppsala, pp 789– 797

  16. Hong Y, Zhang J, Ma B, Yao J, Zhou G, Zhu Q (June 2011) Using cross-entity inference to improve event extraction. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Portland, pp 1127–1136

  17. Li Q, Ji H, Huang L (2013) Joint event extraction via structured prediction with global features. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 73–82

  18. Li Q, Ji H, Hong Y, Li S (2014) Constructing information networks using one single model. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Doha, pp 1846–1851

  19. Wei S, Korostil I, Nothman J, Hachey B (2017) English event detection with translated language features. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Association for Computational Linguistics, Vancouver, pp 293–298

  20. Nguyen T H, 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: Human Language Technologies, pp 300–309

  21. 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: McIlraith S A, Weinberger K Q (eds) Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18). AAAI Press, New Orleans, pp 5916–5923

  22. McCann B, Bradbury J, Xiong C, Socher R (2017) Learned in translation: Contextualized word vectors. In: Guyon I, Luxburg U V, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R (eds) Advances in Neural Information Processing Systems, vol 30. Curran Associates, Inc.

  23. Peters M E, Neumann M, Iyyer M, Gardner M, Clark C, Lee K, Zettlemoyer L (June 2018) Deep contextualized word representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). https://www.aclweb.org/anthology/N18-1202. Association for Computational Linguistics, New Orleans, pp 2227–2237

  24. Devlin J, Chang M-W, Lee K, Toutanova K (June 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: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, pp 4171–4186

  25. Yang Z, Dai Z, Yang Y, Carbonell J, Salakhutdinov R R, Le Q V (2019) Xlnet: Generalized autoregressive pretraining for language understanding. In: Advances in Neural Information Processing Systems, vol 32. Curran Associates, Inc.

  26. Yang W, Xie Y, Lin A, Li X, Tan L, Xiong K, Li M, Lin J (2019) End-to-end open-domain question answering with BERTserini. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations). https://www.aclweb.org/anthology/N19-4013. Association for Computational Linguistics, Minneapolis, pp 72–77

  27. Sakata W, Shibata T, Tanaka R, Kurohashi S (2019) Faq retrieval using query-question similarity and bert-based query-answer relevance. In: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR’19. https://doi.org/10.1145/3331184.3331326. Association for Computing Machinery, New York, pp 1113–1116

  28. Pota M, Ventura M, Fujita H, Esposito M (2021) Multilingual evaluation of pre-processing for bert-based sentiment analysis of tweets. Expert Syst Appl 181:115–119

    Article  Google Scholar 

  29. Guarasci R, Silvestri S, Pietro G D, Fujita H, Esposito M (2021) Assessing bert’s ability to learn italian syntax: A study on null-subject and agreement phenomena. Ambient Intelligence and Humanized Computing

  30. Zhang S, Huang H, Liu J, Li H (2020) Spelling error correction with soft-masked BERT. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. https://www.aclweb.org/anthology/2020.acl-main.82. Association for Computational Linguistics, Online, pp 882–890

  31. Peinelt N, Nguyen D, Liakata M (2020) tBERT: Topic models and BERT joining forces for semantic similarity detection. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. https://www.aclweb.org/anthology/2020.acl-main.630. Association for Computational Linguistics, Online, pp 7047–7055

  32. Yang S, Feng D, Qiao L, Kan Z, Li D (July 2019) Exploring pre-trained language models for event extraction and generation. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. https://www.aclweb.org/anthology/P19-1522. Association for Computational Linguistics, Florence, pp 5284–5294

  33. Sabharwal N, Agrawal A (2021) Hands-on question answering systems with bert. Apress, Berkeley, pp 173–178

    Book  Google Scholar 

  34. Lin J C-W, Shao Y, Djenouri Y, Yun U (2021) Asrnn: A recurrent neural network with an attention model for sequence labeling. Knowl-Based Syst 212:106548. https://doi.org/10.1016/j.knosys.2020.106548, https://www.sciencedirect.com/science/article/pii/S0950705120306778

    Article  Google Scholar 

  35. Catelli R, Casola V, De Pietro G, Fujita H, Esposito M (2021) Combining contextualized word representation and sub-document level analysis through bi-lstm+crf architecture for clinical de-identification. Knowl-Based Syst 213:106649. https://doi.org/10.1016/j.knosys.2020.106649, https://www.sciencedirect.com/science/article/pii/S0950705120307784

    Article  Google Scholar 

  36. Chen Y, Yang H, Liu K, Zhao J, Jia Y (2018) Collective event detection via a hierarchical and bias tagging networks with gated multi-level attention mechanisms. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, pp 1267–1276

  37. Srivastava N, Hinton G E, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958

    MathSciNet  MATH  Google Scholar 

  38. Liu S, Chen Y, Liu K, Zhao J (July 2017) Exploiting argument information to improve event detection via supervised attention mechanisms. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Vancouver, pp 1789–1798

  39. Kingma D P, Ba J (2015) Adam: A method for stochastic optimization. In: Bengio Y, LeCun Y (eds) 3rd International Conference on Learning Representations, ICLR 2015. Conference Track Proceedings, San Diego

  40. Qi P, Zhang Y, Zhang Y, Bolton J, Manning C D (2020) Stanza: A Python natural language processing toolkit for many human languages. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

  41. Liu J, Chen Y, Liu K, Bi W, Liu X (2020) Event extraction as machine reading comprehension. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, Online, pp 1641–1651. https://www.aclweb.org/anthology/2020.emnlp-main.128

  42. 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). https://www.aclweb.org/anthology/2020.emnlp-main.49. Association for Computational Linguistics, Online, pp 671–683

  43. Pennington J, Socher R, Manning CD (2014) Glove: Global vectors for word representation. In: Empirical Methods in Natural Language Processing, pp 1532–1543. http://www.aclweb.org/anthology/D14-1162

  44. Pota M, Marulli F, Esposito M, De Pietro G, Fujita H (2019) Multilingual pos tagging by a composite deep architecture based on character-level features and on-the-fly enriched word embeddings. Knowl-Based Syst 164:309–323. https://doi.org/10.1016/j.knosys.2018.11.003, https://www.sciencedirect.com/science/article/pii/S0950705118305392

    Article  Google Scholar 

  45. Esposito M, Damiano E, Minutolo A, De Pietro G, Fujita H (2020) Hybrid query expansion using lexical resources and word embeddings for sentence retrieval in question answering. Inf Sci 514:88–105. https://doi.org/10.1016/j.ins.2019.12.002, https://www.sciencedirect.com/science/article/pii/S0020025519311107

    Article  Google Scholar 

  46. Ou J, Li Y, Shen C (2021) Unlabeled pca-shuffling initialization for convolutional neural networks. Appl Intell 48:4565–4576. https://doi.org/10.1007/s10489-018-1230-2

    Article  Google Scholar 

  47. Qin J, Zeng X, Wu S (2021) E-gcn: graph convolution with estimated labels. Appl Intell 51:5007–5015. https://doi.org/10.1007/s10489-020-02093-5

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the State Grid Corporation of China through the Project Research on Key Technologies of Knowledge Graph in Power System Fault Management under Grant 52010119000F.

Author information

Authors and Affiliations

  1. School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, 100876, China

    Shudong Lu, Si Li, Yajing Xu & Jun Guo

  2. State Grid Jibei Electric Power Company Limited, Beijing, 100053, China

    Kai Wang & Haibo Lan

Authors
  1. Shudong Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Si Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yajing Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Kai Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Haibo Lan
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jun Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Si Li.

Additional information

Publisher’s note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lu, S., Li, S., Xu, Y. et al. Event detection from text using path-aware graph convolutional network. Appl Intell 52, 4987–4998 (2022). https://doi.org/10.1007/s10489-021-02695-7

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-021-02695-7

Keywords

Search

Navigation