Open Access
ARTICLE
Combing Type-Aware Attention and Graph Convolutional Networks for Event Detection
Kun Ding1, Lu Xu2, Ming Liu1, Xiaoxiong Zhang1, Liu Liu1, Daojian Zeng2,*, Yuting Liu1,3, Chen Jin4
1 The Sixty-Third Research Institute, National University of Defense Technology, Nanjing, 210007, China
2 Hunan Normal University, Changsha, 410000, China
3 School of Computer & Software, Nanjing University of Information Science and Technology, Nanjing, 210044, China
4 School of Computer Science, University of Manchester, Manchester, M13 9PL, UK
* Corresponding Author: Daojian Zeng. Email:
Computers, Materials & Continua 2023, 74(1), 641-654. https://doi.org/10.32604/cmc.2023.031052
Received 09 April 2022; Accepted 11 May 2022; Issue published 22 September 2022
Abstract
Event detection (ED) is aimed at detecting event occurrences and categorizing them. This task has been previously solved via recognition and classification of event triggers (ETs), which are defined as the phrase or word most clearly expressing event occurrence. Thus, current approaches require both annotated triggers as well as event types in training data. Nevertheless, triggers are non-essential in ED, and it is time-wasting for annotators to identify the “
most clearly” word from a sentence, particularly in longer sentences. To decrease manual effort, we evaluate event detection without triggers. We propose a novel framework that combines Type-aware Attention and Graph Convolutional Networks (TA-GCN) for event detection. Specifically, the task is identified as a multi-label classification problem. We first encode the input sentence using a novel type-aware neural network with attention mechanisms. Then, a Graph Convolutional Networks (GCN)-based multi-label classification model is exploited for event detection. Experimental results demonstrate the effectiveness.
Keywords
Cite This Article
K. Ding, L. Xu, M. Liu, X. Zhang, L. Liu
et al., "Combing type-aware attention and graph convolutional networks for event detection,"
Computers, Materials & Continua, vol. 74, no.1, pp. 641–654, 2023. https://doi.org/10.32604/cmc.2023.031052