Improving event detection via open-domain event trigger knowledge

• Main Authors: TONG, Meihan, XU, Bin, WANG, Shuai, CAO, Yixin, HOU, Lei, LI, Juanzi, XIE, Jun
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2020
• Subjects: Databases and Information Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/7450; https://ink.library.smu.edu.sg/context/sis_research/article/8453/viewcontent/2020.acl_main.522.pdf
• Institution: Singapore Management University

Event Detection (ED) is a fundamental task in automatically structuring texts. Due to the small scale of training data, previous methods perform poorly on unseen/sparsely labeled trigger words and are prone to overfitting densely labeled trigger words. To address the issue, we propose a novel Enrichment Knowledge Distillation (EKD) model to leverage external open-domain trigger knowledge to reduce the in-built biases to frequent trigger words in annotations. Experiments on benchmark ACE2005 show that our model outperforms nine strong baselines, is especially effective for unseen/sparsely labeled trigger words. The source code is released on https://github.com/shuaiwa16/ekd.git.