Skip to main content
SpringerLink
Log in

Empower Chinese event detection with improved atrous convolution neural networks

  • Review
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Event Detection (ED) is an essential and challenging task in Information Extraction (IE). Recent advances in neural networks make it possible to build reliable models without complicated feature engineering. Neural network-based models commonly regard event detection as a char-wise or word-wise labeling task, which suffers from the problems of long-distance information miss-capturing, discontinuous labeling errors, etc., between characters/words and event triggers, especially in languages without natural word delimiters such as Chinese. In this paper, we propose a novel multi-layer Residual and Gated-Based Atrous Convolution Neural Network (RG-ACNN) framework, which attempts to alleviate above-mentioned problems. Specifically, the ACNN is introduced in our model to expand the receptive field to obtain multi-scale context information to capture dependencies between long-distance information. While gated and residual mechanisms are both imported to ACNN to improve our networks’ capability of the information filtering and aggregation. Besides, RG-ACNN performs event detection in a char-wise paradigm, where a novel “head-tail dual-pointer” labeled strategy is used to overcome the incomplete continuous labeling problem. Experiments on the ACE2005-CN and several standard benchmark datasets show that RG-ACNN significantly outperforms state-of-the-art (SOTA) methods.

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. B: Begin, I: Intermediate, E: End, S: Single, O: Other.

References

  1. Ghaeini R, Fern XZ, Huang L, Tadepalli P (2016) Event nugget detection with forward-backward recurrent neural networks. In: The 54th annual meeting of the association for computational linguistics, vol 2, pp 369–337

  2. Nguyen TH, Grishman T (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, vol 2, pp 365–371

  3. 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, vol 1, pp 167–176

  4. Liu H, Lu Y, Han X, Sun L (2018) Nugget proposal networks for chinese event detection. In: Proceedings of the 56th annual meeting of the association for computational linguistics vol 1, pp 1565–1574

  5. Zeng Y, Yang H, Feng Y, Wang Z, Zhao D (2016) A convolution BiLSTM neural network model for Chinese event extraction. In: Natural Language Understanding and Intelligent Applications. pp 275–287

  6. Chen Z, Ji H (2009) Language specific issue and feature exploration in Chinese event extraction. In: Proceedings of Human language technologies: the 2009 annual conference of the north american chapter of the association for computational linguistics. pp. 209–121

  7. Gehring J, Auli M, Grangier D, Yarats D, Dauphin YN (2017) Convolutional sequence to sequence learning. In: Proceedings of the 34th international conference on machine learning. pp. 1243–1252

  8. Chieu HL, Ng HT (2002) A maximum entropy approach to information extraction from semi-structured and free text. In: Eighteenth national conference on Artificial intelligence. American Association for Artificial Intelligence. pp 786–791

  9. Ahn D (2006) The stages of event extraction. In: Proceedings of the workshop on annotating and reasoning about time and events. pp 1–8

  10. Li Q, Ji H, Yu H, Li S (2014) Constructing information networks using one single model. In: Proceedings of the 2014 conference on empirical methods in natural language processing, pp 1846–1851

  11. Hong Y, Zhang J, Ma B, Yao J, Zhao G, Zhu Q (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, vol 1, pp 1127–1136

  12. Ji H, Grishman R (2008) Refining event extraction through cross-document inference. In: 46th annual meeting of the association for computational linguistics: human language technologies, ACL-08: HLT. pp 254–262

  13. 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, pp 789–797

  14. Li P, Zhu Q, Zhu G (2013) Joint modeling of argument identification and role determination in Chinese event extraction with discourse-level information. In: Twenty-Third international joint conference on artificial intelligence, pp 2120–2126

  15. Chen C, Ng V (2012) Joint modeling for Chinese event extraction with rich linguistic features. In: Proceedings of COLING, pp 529–544

  16. Li P, Zhou G, Zhu Q, Hou L (2012) Employing compositional semantics and discourse consistency in Chinese event extraction. In: Proceedings of the 2012 joint conference on empirical methods in natural language processing and computational natural language learning, pp 1006–1016

  17. Nguyen TH, Grishman R (2016) Modeling skip-grams for event detection with convolutional neural networks. In: Proceedings of the 2016 conference on empirical methods in natural language, pp 886–891

  18. 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: human language technologies, pp 300–309

  19. He X, Li L (2017) Trigger detection based on bidirectional LSTM and two-stage method. J Chin Inf Process 31(6):147–154

    Google Scholar 

  20. Feng X, Qin B, Liu T (2018) A language-independent neural network for event detection. Sci China Inf Sci Sci China Inf Sci 61(9):092–106

    Google Scholar 

  21. Chen B, Zhou Y (2019) Event trigger word extraction based on convolutional bidirectional long short term memory network. Comput Eng 45(1):153–158

    MathSciNet  Google Scholar 

  22. Wang K, Hong Y (2018) Combining context dependency and sentence semantic representation for event nugget detection. J Fornt Comput Sci Technol 12(3):423–431

    MathSciNet  Google Scholar 

  23. Liu J, Chen Y, Liu K, Zhao J (2018) Event detection via gated multilingual attention mechanism. In: Thirty-Second AAAI conference on artificial intelligence

  24. Li L, Wan J, Zheng J, Wang J (2018) Biomedical event extraction based on GRU integrating attention mechanism. BMC Bioinformatics 19(9):177

    Google Scholar 

  25. Ramamoorthy S, Murugan S (2018) An attentive sequence model for adverse drug event extraction from biomedical text

  26. Zhang T, Ji H (2018) Event extraction with generative adversarial imitation learning

  27. Mu X, Xu A (2019) A character-level BiLSTM-CRF model with multi-representations for chinese event detection. IEEE Access 7(2019):146524–146532

    Article  Google Scholar 

  28. Song Y, Shi S, Li J, Zhang H (2018) Directional skip-gram: explicitly distinguishing left and right context for word embeddings. In: Proceedings of the 2018 conference of the north american chapter of the association for computational linguistics: human language technologies, vol 2, pp 175–180

  29. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Polosukhin I (2017) Attention is all you need, Advances in neural information processing systems, pp 5998–6008

  30. Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions

  31. Wang P, Chen P, Yuan Y, Liu D, Huang Z, Hou X, Cottrell G (2018) Understanding convolution for semantic segmentation, 2018 IEEE winter conference on applications of computer vision (WACV), pp 1451–1460

  32. Chang SY, Li B, Simko G, Sainath TN, Tripthi A (2018) A. vanden Oord and O. Vinyals, Temporal modeling using dilated convolution and gating for voice-activity-detection. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 5549–5553

  33. Van den Oord A, Kalchbrenner N, Espeholt L, Vinyals O, Graves A (2016) Conditional image generation with PixelCNN decoders. In: Proceedings of the 30th international conference on neural information processing systems, pp 4790–4798

  34. Dauphin YN, Fan A, Auli M, Grangier D (2017) Language modeling with gated convolutional networks. In: Proceedings of the 34th international conference on machine learning, vol 70, pp 933–941

  35. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  36. You L, Liu K (2005) Building chinese framenet database. In: 2005 international conference on natural language processing and knowledge engineering, pp 301–306

Download references

Acknowledgements

This research is financially supported by The National Key Research and Development Program of China (Grant Number 2018YFC0807105), National Natural Science Foundation of China (Grant Number 61462073) and Science and Technology Committee of Shanghai Municipality (STCSM) (Under Grant Numbers 17DZ1101003, 18511106602 and 18DZ2252300).

Author information

Authors and Affiliations

  1. East China University of Science and Technlogy, Shanghai, China

    Zhihong Wang, Yi Guo & Jiahui Wang

  2. National Engineering Laboratory for Big Data Distribution and Exchange Technologies, Shanghai, China

    Yi Guo

  3. Shanghai Engineering Research Center of Big Data & Internet Audience, Shanghai, China

    Yi Guo

Authors
  1. Zhihong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yi Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jiahui Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yi Guo.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

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

Wang, Z., Guo, Y. & Wang, J. Empower Chinese event detection with improved atrous convolution neural networks. Neural Comput & Applic 33, 5805–5820 (2021). https://doi.org/10.1007/s00521-020-05360-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-020-05360-1

Keywords

Search

Navigation