Shunyu Yao
ABSTRACT
Financial event extraction aims to detect events from financial announcements and extract corresponding event arguments. This task is challenging because financial announcements are often long text, the arguments of an event are always scattered among different sentences in the document, and multiple events can coexist in the same document. It requires a comprehensive understanding of the document and the ability to aggregate arguments across multiple sentences. Most existing sentence-level event extraction methods only extract event arguments within the sentence range. These methods are not very effective for this task, and it is difficult to handle a large number of financial announcements. To address these issues, we propose a novel heterogeneous graph-based model HGCFEE with six types of edges designed to capture the interactions between sentences and entities using heterogeneous graphs. In-depth experiments and comprehensive analysis demonstrate the superiority of HGCFEE over baseline methods.
- D. Ahn, ‘The stages of event extraction’, in Proceedings of the Workshop on Annotating and Reasoning about Time and Events, Sydney, Australia, 2006, pp. 1–8. Accessed: Jul. 15, 2022. [Online]. Available: https://aclanthology.org/W06-0901Google Scholar
Cross Ref
- S. Liao and R. Grishman, ‘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, 2010, pp. 789–797. Accessed: Jul. 15, 2022. [Online]. Available: https://aclanthology.org/P10-1081Google Scholar
- Y. Hong, J. Zhang, B. Ma, J. Yao, G. Zhou, and Q. Zhu, ‘Using Cross-Entity Inference to Improve Event Extraction’, in Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, Oregon, USA, 2011, pp. 1127–1136. Accessed: Jul. 15, 2022. [Online]. Available: https://aclanthology.org/P11-1113Google Scholar
- B. Yang and T. M. Mitchell, ‘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: Human Language Technologies, San Diego, California, 2016, pp. 289–299. doi: 10.18653/v1/N16-1033.Google ScholarCross Ref
- T. H. Nguyen and R. Grishman, ‘Modeling Skip-Grams for Event Detection with Convolutional Neural Networks’, in Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Texas, 2016, pp. 886–891. doi: 10.18653/v1/D16-1085.Google ScholarCross Ref
- L. Sha, F. Qian, B. Chang, and Z. Sui, ‘Jointly Extracting Event Triggers and Arguments by Dependency-Bridge RNN and Tensor-Based Argument Interaction’, in Proceedings of the AAAI Conference on Artificial Intelligence, Apr. 2018, vol. 32. doi: 10.1609/aaai.v32i1.12034.Google ScholarCross Ref
- S. Yang, D. Feng, L. Qiao, Z. Kan, and D. Li, ‘Exploring Pre-trained Language Models for Event Extraction and Generation’, in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, Jul. 2019, pp. 5284–5294. doi: 10.18653/v1/P19-1522.Google ScholarCross Ref
- J. Liu, Y. Chen, K. Liu, W. Bi, and X. Liu, ‘Event Extraction as Machine Reading Comprehension’, in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online, Nov. 2020, pp. 1641–1651. doi: 10.18653/v1/2020.emnlp-main.128.Google ScholarCross Ref
- H. Yang, Y. Chen, K. Liu, Y. Xiao, and J. Zhao, ‘DCFEE: A Document-level Chinese Financial Event Extraction System based on Automatically Labeled Training Data’, in Proceedings of ACL 2018, System Demonstrations, Melbourne, Australia, 2018, pp. 50–55. doi: 10.18653/v1/P18-4009.Google ScholarCross Ref
- E. Riloff, ‘Automatically constructing a dictionary for information extraction tasks’, in Proceedings of the eleventh national conference on Artificial intelligence, Washington, D.C., Jul. 1993, pp. 811–816.Google Scholar
- M. Naughton, N. Kushmerick, and J. Carthy, ‘Event extraction from heterogeneous news sources’, in proceedings of the AAAI workshop event extraction and synthesis, 2006, pp. 1–6.Google Scholar
- Y. Chen, L. Xu, K. Liu, D. Zeng, and J. Zhao, ‘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, 2015, pp. 167–176. doi: 10.3115/v1/P15-1017.Google ScholarCross Ref
- T. H. Nguyen and R. Grishman, ‘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, 2015, pp. 365–371. doi: 10.3115/v1/P15-2060.Google ScholarCross Ref
- X. Feng, L. Huang, D. Tang, H. Ji, B. Qin, and T. Liu, ‘A Language-Independent Neural Network for Event Detection’, in Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Berlin, Germany, 2016, pp. 66–71. doi: 10.18653/v1/P16-2011.Google ScholarCross Ref
- P. Ding, L. Zhuoqian, and D. Yuan, ‘Textual Information Extraction Model of Financial Reports’, in Proceedings of the 2019 7th International Conference on Information Technology: IoT and Smart City, New York, NY, USA, Dec. 2019, pp. 404–408. doi: 10.1145/3377170.3377231.Google ScholarDigital Library
- S. Hochreiter and J. Schmidhuber, ‘Long Short-Term Memory’, Neural Computation, vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735.Google ScholarDigital Library
- J. D. Lafferty, A. McCallum, and F. C. N. Pereira, ‘Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data’, in Proceedings of the Eighteenth International Conference on Machine Learning, San Francisco, CA, USA, Jun. 2001, pp. 282–289.Google Scholar
- J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, ‘BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding’. arXiv, May 24, 2019. doi: 10.48550/arXiv.1810.04805.Google Scholar
- Z. Huang, W. Xu, and K. Yu, ‘Bidirectional LSTM-CRF Models for Sequence Tagging’. arXiv, Aug. 09, 2015. doi: 10.48550/arXiv.1508.01991.Google Scholar
- T. N. Kipf and M. Welling, ‘Semi-Supervised Classification with Graph Convolutional Networks’, In 5th International Conference on Learning Representations (ICLR), Toulon, France, April 24-26, 2017, Conference Track Proceedings.Google Scholar
- S. Zheng, W. Cao, W. Xu, and J. Bian, ‘Doc2EDAG: An End-to-End Document-level Framework for Chinese Financial Event Extraction’, in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, Nov. 2019, pp. 337–346. doi: 10.18653/v1/D19-1032.Google ScholarCross Ref
Index Terms
- Heterogeneous Graph Neural Network for Chinese Financial Event Extraction
Recommendations
MHGEE: Event Extraction via Multi-granularity Heterogeneous Graph
Computational Science – ICCS 2022AbstractEvent extraction is a key task of information extraction. Existing methods are not effective due to two challenges of this task: 1) Most of previous methods only consider a single granularity information and they are often insufficient to ...
Seq2EG: a novel and effective event graph parsing approach for event extraction
AbstractEvent extraction is a fundamental task in information extraction. Most previous approaches typically transform event extraction into two subtasks: trigger classification and argument classification, and solve them via classification-based methods, ...
Contrastive Learning for Event Extraction
ICMLSC '22: Proceedings of the 2022 6th International Conference on Machine Learning and Soft ComputingEvent extraction is an important information extraction task, aiming at extracting event information from text. Each event consists of triggers and arguments with specific roles. Event extraction methods first identify the trigger and classify it into ...
Comments