Skip to main content
SpringerLink
Log in

Exploiting a More Global Context for Event Detection Through Bootstrapping

  • Conference paper
  • First Online:
Book cover Advances in Information Retrieval (ECIR 2019)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 11437))

Included in the following conference series:

Abstract

Over the last few years, neural models for event extraction have obtained interesting results. However, their application is generally limited to sentences, which can be an insufficient scope for disambiguating some occurrences of events. In this article, we propose to integrate into a convolutional neural network the representation of contexts beyond the sentence level. This representation is built following a bootstrapping approach by exploiting an intra-sentential convolutional model. Within the evaluation framework of TAC 2017, we show that our global model significantly outperforms the intra-sentential model while the two models are competitive with the results obtained by TAC 2017 participants.

Work partly supported by ANR under project ASRAEL (ANR-15-CE23-0018).

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 109.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 139.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    We use the basic dependencies provided by par Stanford CoreNLP [13].

  2. 2.

    https://github.com/mgormley/concrete-chunklink.

References

  1. Bies, A., et al.: A Comparison of event representations in DEFT. in: fourth workshop on events, pp. 27–36. San Diego, June 2016. http://www.aclweb.org/anthology/W16-1004

  2. Chen, Y., Xu, L., Liu, K., Zeng, D., Zhao, J.: Event extraction via dynamic multi-pooling convolutional neural networks. In: 53rd Annual Meeting of the Association for Computational Linguistics and 7th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2015), Beijing, China, pp. 167–176 (2015)

    Google Scholar 

  3. Duan, S., He, R., Zhao, W.: Exploiting document level information to improve event detection via recurrent neural networks. In: Eighth International Joint Conference on Natural Language Processing (IJCNLP 2017), Taipei, Taiwan, pp. 352–361 (2017). https://aclanthology.coli.uni-saarland.de/papers/I17-1036/i17-1036

  4. Feng, X., Huang, L., Tang, D., Ji, H., Qin, B., Liu, T.: A language-independent neural network for event detection. In: 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016), Berlin, Germany, pp. 66–71 (2016). https://doi.org/10.18653/v1/P16-2011. https://aclanthology.coli.uni-saarland.de/papers/P16-2011/p16-2011

  5. Gimpel, K., Smith, N.: Softmax-Margin CRFs: training log-linear models with cost functions. In: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies: (NAACL HLT 2010), Los Angeles, California, pp. 733–736 (2010)

    Google Scholar 

  6. Jiang, S., Li, Y., Qin, T., Meng, Q., Dong, B.: SRCB Entity Discovery and Linking (EDL) and event nugget systems for TAC 2017. In: Text Analysis Conference (TAC) (2017)

    Google Scholar 

  7. Jorge, A.M., Campos, R., Jatowt, A., Nunes, S. (eds.): First Workshop on Narrative Extraction From Text (Text2Story 2018). Grenoble, France (2018)

    Google Scholar 

  8. Kim, Y.: Convolutional neural networks for sentence classification. In: EMNLP (2014)

    Google Scholar 

  9. Kodelja, D., Besançon, R., Ferret, O., Le Borgne, H., Boros, E.: CEA LIST participation to the TAC 2017 event nugget track. In: Text Analysis Conference (TAC) (2017)

    Google Scholar 

  10. Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: 31st International Conference on International Conference on Machine Learning (ICML 2014), Beijing, China, pp. 1188–1196 (2014)

    Google Scholar 

  11. Liao, S., Grishman, R.: Using document level cross-event inference to improve event extraction. In: ACL (2010)

    Google Scholar 

  12. Makarov, P., Clematide, S.: UZH at TAC KBP 2017: event nugget detection via joint learning with Softmax-Margin Objective. In: Text Analysis Conference (TAC) (2017)

    Google Scholar 

  13. Manning, C.D., Surdeanu, M., Bauer, J., Finkel, J., Bethard, S.J., McClosky, D.: The stanford CoreNLP natural language processing Toolkit. In: 52nd Annual Meeting of the Association for Computational Linguistics (ACL 2014), system demonstrations, pp. 55–60 (2014)

    Google Scholar 

  14. Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: 26th International Conference on Neural Information Processing Systems (NIPS 2013), Lake Tahoe, Nevada, pp. 3111–3119 (2013)

    Google Scholar 

  15. Mitamura, T., Liu, Z., Hovy, E.: Events detection, coreference and sequencing: what’s next? overview of the TAC KBP 2017 Event Track. In: Text Analysis Conference (TAC) (2017)

    Google Scholar 

  16. Nguyen, T.H., Cho, K., Grishman, R.: Joint event extraction via recurrent neural networks. In: 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT 2016), San Diego, California, pp. 300–309 (2016)

    Google Scholar 

  17. Nguyen, T.H., Grishman, R.: Event detection and domain adaptation with convolutional neural networks. In: 53rd Annual Meeting of the Association for Computational Linguistics and 7th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2015), Beijing, China, pp. 365–371 (2015)

    Google Scholar 

  18. Nguyen, T.H., Grishman, R., Meyers, A.: New york university 2016 system for KBP event nugget: a deep learning approach. In: Text Analysis Conference (TAC) (2016)

    Google Scholar 

  19. Reimers, N., Gurevych, I.: Reporting score distributions makes a difference: performance study of LSTM-networks for sequence tagging. In: 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017), Copenhagen, Denmark, pp. 338–348 (2017)

    Google Scholar 

  20. Zhao, Y., Jin, X., Wang, Y., Cheng, X.: Document embedding enhanced event detection with hierarchical and supervised attention. In: 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), pp. 414–419. Association for Computational Linguistics (2018)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. CEA, LIST, Laboratoire Analyse Sémantique Texte et Image, 91191, Gif-sur-Yvette, France

    Dorian Kodelja, Romaric Besançon & Olivier Ferret

Authors
  1. Dorian Kodelja
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Romaric Besançon
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Olivier Ferret
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dorian Kodelja .

Editor information

Editors and Affiliations

  1. University of Strathclyde, Glasgow, UK

    Leif Azzopardi

  2. Bauhaus Universität Weimar, Weimar, Germany

    Benno Stein

  3. Universität Duisburg-Essen, Duisburg, Germany

    Norbert Fuhr

  4. GESIS - Leibniz Institute for the Social Sciences, Cologne, Germany

    Philipp Mayr

  5. Delft University of Technology, Delft, The Netherlands

    Claudia Hauff

  6. University of Twente, Enschede, The Netherlands

    Djoerd Hiemstra

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Kodelja, D., Besançon, R., Ferret, O. (2019). Exploiting a More Global Context for Event Detection Through Bootstrapping. In: Azzopardi, L., Stein, B., Fuhr, N., Mayr, P., Hauff, C., Hiemstra, D. (eds) Advances in Information Retrieval. ECIR 2019. Lecture Notes in Computer Science(), vol 11437. Springer, Cham. https://doi.org/10.1007/978-3-030-15712-8_51

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-15712-8_51

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-15711-1

  • Online ISBN: 978-3-030-15712-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation