Paper Info
Title
Multi-Graph Convolution Network With Jump Connection For Event Detection
Abstract
Event detection is an important information extraction task in nature language processing. Recently, the method based on syntactic information and graph convolution network has been wildly used in event detection task and achieved good performance. For event detection, graph convolution network (GCN) based on dependency arcs can capture the sentence syntactic representations and the syntactic information, which is from candidate triggers to arguments. However, existing methods based on GCN with dependency arcs suffer from imbalance and redundant information in graph. To capture important and refined information in graph, we propose Multi-graph Convolution Network with Jump Connection (MGJ-ED). The multi-graph convolution network module adds a core subgraph splitted from dependency graph which selects important one-hop neighbors' syntactic information in breadth via GCN. Also the jump connection architecture aggregate GCN layers' representation with different attention score, which learns the importance of neighbors' syntactic information of different hops away in depth. The experimental results on the widely used ACE 2005 dataset shows the superiority of the other state-of-the-art methods.
Year
DOI
Venue
2019
10.1109/ICTAI.2019.00108
2019 IEEE 31ST INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2019)
Keywords
Field
DocType
event detection, multi-graph convolution network, jump connection aggregation, bias loss function, syntactic information in breadth and depth
Graph,Pattern recognition,Computer science,Convolution,Theoretical computer science,Information extraction,Network module,Artificial intelligence,Jump,Syntax,Dependency graph,Sentence
Conference
ISSN
Citations 
PageRank 
1082-3409
0
0.34
References 
Authors
20
6
Name
Order
Citations
PageRank
Xiangbin Meng100.34
Pengfei Wang216814.35
Haoran Yan300.34
Liutong Xu4368.81
Jiafeng Guo51737102.17
Yixing Fan620219.39