MBCED: Multi-task learning event detection method based on pre-training
Article No.: 59, Pages 1 - 6
Abstract
Event detection is the first step in event extraction. Its goal is to filter out event sentences containing event information from candidate texts and determine their types. In order to solve the problem of sparse corpus and inaccurate judgment of the trigger word type caused by the polysemy of the trigger word in the existing event detection methods, this paper proposes a multi-task learning event detection method based on pre-training - MBCED, which performs event detection and word sense disambiguation tasks at the same time, transfers the knowledge learned in the word sense disambiguation task to the event detection task, which not only supplements the corpus, but also alleviates the inaccuracy of trigger word classification to a certain extent . Experiments on the ACE2005 dataset prove that the MBCED method has better event detection performance compared with existing methods.
References
[1]
Yang, B., & Mitchell, T. (2016). Joint extraction of events and entities within a document context. arXiv preprint arXiv:1609.03632.
[2]
Liu, X., Luo, Z., & Huang, H. (2018). Jointly multiple events extraction via attention-based graph information aggregation. arXiv preprint arXiv:1809.09078.
[3]
Liu, X., Gao, J., He, X., D Li, & Wang, Y. Y. . (2015). Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
[4]
Daumé III, H. (2009). Bayesian multitask learning with latent hierarchies. arXiv preprint arXiv:0907.0783.
[5]
Prettenhofer, P., & Stein, B. (2010, July). Cross-language text classification using structural correspondence learning. In Proceedings of the 48th annual meeting of the association for computational linguistics (pp. 1118-1127).
[6]
Liu, S., Chen, Y., He, S., Liu, K., & Zhao, J. (2016). Leveraging FrameNet to Improve Automatic Event Detection. Meeting of the Association for Computational Linguistics.
[7]
Lu, Y., Lin, H., Han, X., & Sun, L. (2019, July). Distilling discrimination and generalization knowledge for event detection via delta-representation learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (pp. 4366-4376).
[8]
Tong, M., Xu, B., Wang, S., Cao, Y., Hou, L., Li, J., & Xie, J. (2020, July). Improving event detection via open-domain trigger knowledge. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 5887-5897).
[9]
Chen, Y., Xu, L., Kang, L., Zeng, D., & Zhao, J. . (2015). Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks. The 53rd Annual Meeting of the Association for Computational Linguistics(ACL2015).
[10]
Nguyen, T. H., Cho, K., & Grishman, R. . (2016). Joint Event Extraction via Recurrent Neural Networks. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
[11]
Liu, J., Chen, Y., Liu, K., & Zhao, J. (2018, April). Event detection via gated multilingual attention mechanism. In Thirty-Second AAAI conference on artificial intelligence.
[12]
Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
[13]
Lafferty, J., Mccallum, A., & Pereira, F. . (2001). Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. Proc. 18th International Conf. on Machine Learning.
[14]
Xu, H., Ren, Z., Shi, J., & Zhou, H. . (2016). An improved chinese word segmentation method based on chain conditional random fields. Computer Applications and Software.
[15]
Duo-qian, Q. Q. Q. M., & ZHANG, Z. F. (2013). Named Entity Recognition on Chinese Microblog [J]. Computer Science, 6.
[16]
Chen, C., & Ng, V. (2012, December). Joint modeling for chinese event extraction with rich linguistic features. In Proceedings of COLING 2012 (pp. 529-544).
Recommendations
Event Detection via Context Understanding Based on Multi-task Learning
Event detection (ED) aims to identify events of interest described in the text. With the current explosive growth of text data on the internet, ED is increasingly practical and has gained many researchers’ attention. The existing works usually design ED ...
Unifying Event Detection and Captioning as Sequence Generation via Pre-training
Computer Vision – ECCV 2022AbstractDense video captioning aims to generate corresponding text descriptions for a series of events in the untrimmed video, which can be divided into two sub-tasks, event detection and event captioning. Unlike previous works that tackle the two sub-...
Learning, detection and representation of multi-agent events in videos
In this paper, we model multi-agent events in terms of a temporally varying sequence of sub-events, and propose a novel approach for learning, detecting and representing events in videos. The proposed approach has three main steps. First, in order to ...
Comments
Information & Contributors
Information
Published In
December 2021
699 pages
ISBN:9781450385053
DOI:10.1145/3508546
Copyright © 2021 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 25 February 2022
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- Science and Technology on Information System Engineering Laboratory
- National Natural Science Foundation of China
- National Social Science Foundation
Conference
ACAI'21
ACAI'21: 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence
December 22 - 24, 2021
Sanya, China
Acceptance Rates
Overall Acceptance Rate 173 of 395 submissions, 44%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 32Total Downloads
- Downloads (Last 12 months)2
- Downloads (Last 6 weeks)1
Reflects downloads up to 09 Nov 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format