Event Extraction with Spectrum Estimation Using Neural Networks Linear Methods

Vuyyuru Madhavi

doi:10.4108/eetsis.4355

Authors

Vuyyuru Madhavi Eswar College of Engineering

DOI:

https://doi.org/10.4108/eetsis.4355

Keywords:

Spectrum estimation, Event extraction, Movie scene arguments extraction, Scene trigger extraction, Graph attention system

Abstract

The timely extraction of event information from enormous amounts of textual data is a critical research problem. Event extraction using deep learning technology has gained academic attention as a result of the fast growth of deep learning. Event extraction requires costly, expert-level, high-quality human annotations. As a result, developing a data-efficient event extraction model that can be trained using only a few labelled samples has emerged as a key difficulty. Existing research work focuses mainly on the structured data with supervised models. The proposed work focuses on Movie Scene Event Extraction, a practical media analysis problem that seeks to extract structured events from unstructured movie screenplays. We suggest using the correlation between various argument roles in situations where different argument roles in a movie scene share similar qualities. This can be beneficial to the Movie Scene Argument Extraction (argument classification and identification) and film scene trigger extraction (Trigger recognition and classifying). In order to represent the relation between different roles in argument and their respective roles, we propose a Superior Concept of Role (SRC) as a top-level idea of a role that is based on the classic argument role, as well as an SRC-based Graph Attention System (GAT). To assess the efficacy of the model we designed, we constructed the dataset MovieSceneEvent to extract movies’ scene-related events. Additionally, we conducted tests on an existing dataset in order to compare results with different models. Results from the experiments like extraction of words, aspect keywords from the documents indicate that our model does better than other models. Furthermore, the information on the relationship between the argument roles helps improve the effectiveness of film scene extraction of events.

References

Mcclosky, D.; Surdeanu, M.; Manning, C.D. Event Extraction as Dependency Parsing. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, OR, USA, 19–24 June 2011; pp. 1626–1635.

Liao, R. Using Document Level Cross-Event Inference to Improve Event Extraction. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, Uppsala, Sweden, 11–16 July 2010; pp. 789–797.

Li, Q.; Ji, H.; Huang, L. Joint Event Extraction via Structured Prediction with Global Features. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, Sofia, Bulgaria, 4–9 August 2013; pp. 73–82.

Ji, H.; Grishman, R. Refining Event Extraction through Cross-Document Inference. In Proceedings of the ACL-08: HLT, Columbus, OH, USA, 19–20 June 2008; pp. 254–262.

Huang, R.; Riloff, E. Modeling Textual Cohesion for Event Extraction. Proc. AAAI Conf. Artif. Intell. 2021, 26, 1664–1670. [CrossRef]

Sha, L.; Qian, F.; Chang, B.; Chang, B.; Sui, Z. Jointly Extracting Event Triggers and Arguments by Dependency-Bridge Rnn and Tensor-Based Argument Interaction. Proc. AAAI Conf. Artif. Intell. 2018, 32, 5916–5923. [CrossRef]

Nguyen, T.H.; Grishman, R. Graph Convolutional Networks with Argument-Aware Pooling for Event Detection. Proc. AAAI Conf. Artif. Intell. 2018, 32, 5900–5907. [CrossRef]

Nguyen, T.H.; Grishman, R. 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), Beijing, China, 26–31 July 2015; Association for Computational Linguistics: Stroudsburg, PA, USA, 2015.

Chen, Y.; Xu, L.; Liu, K.; Zeng, D.; Zhao, J. 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), Beijing, China, 26–31 July 2015; Association for Computational Linguistics: Stroudsburg, PA, USA, 2015.

Chen, Y.; Chen, T.; Ebner, S.; White, A.S.; Van Durme, B. Reading the Manual: Event Extraction as Definition Comprehension.arXiv 2019, arXiv:1912.01586.

G. Ansmann, R. Karnatak, K. Lehnertz, and U. Feudel, Extreme events in excitable systems and mechanisms of their generation, Phys. Rev. E 88, 052911 (2013).

T. Bódai, G. Károlyi, and T. Tél, Driving a conceptual model clim ate by different processes: Snapshot attractors and extreme events, Phys. Rev. E 87, 022822 (2013).

R. Karnatak, G. Ansmann, U. Feudel, and K. Lehnertz, Route to extreme events in excitable systems, Phys. Rev. E 90, 022917 (2014).

C. Mulhern, S. Bialonski, and H. Kantz, Extreme events due to localization of energy, Phys. Rev. E 91, 012918 (2015).

D. Qi and A. J. Majda, Predicting fat-tailed intermittent probability distributions in passive scalar turbulence with imperfect models through empirical information theory, Commun. Math. Sci. 14, 1687 (2016).

M. A. Mohamad and T. P. Sapsis, Sequential sampling strategy for extreme event statistics in nonlinear dynamical systems, Proc. Natl. Acad. Sci. USA 115, 11138 (2018).

C. T. Bolles, K. Speer, and M. N. J. Moore, Anomalous wave statistics induced by abrupt depth change, Phys. Rev. Fluids 4, 011801(R) (2019).

S. Hallerberg, E. G. Altmann, D. Holstein, and H. Kantz, Precursors of extreme increments, Phys. Rev. E 75, 016706 (2007).

R. V. Donner and S. M. Barbosa, Nonlinear time series analysis in the geosciences, Lect. Notes Earth Sci. 112, 37 (2008).

H. L. D. de S. Cavalcante, M. Oriá, D. Sornette, E. Ott, and D. J. Gauthier, Predictability and Suppression of Extreme Events in a Chaotic System, Phys. Rev. Lett. 111, 198701 (2013).