Multi-graph Convolution Network with Jump Connection for Event Detection

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.

[1]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[2]  Ralph Grishman,et al.  Joint Event Extraction via Recurrent Neural Networks , 2016, NAACL.

[3]  Regina Barzilay,et al.  Multi-Event Extraction Guided by Global Constraints , 2012, NAACL.

[4]  Ralph Grishman,et al.  Using Document Level Cross-Event Inference to Improve Event Extraction , 2010, ACL.

[5]  Jun Zhao,et al.  Exploiting Argument Information to Improve Event Detection via Supervised Attention Mechanisms , 2017, ACL.

[6]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[7]  Zhifang Sui,et al.  Jointly Extracting Event Triggers and Arguments by Dependency-Bridge RNN and Tensor-Based Argument Interaction , 2018, AAAI.

[8]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[9]  Ralph Grishman,et al.  Event Detection and Domain Adaptation with Convolutional Neural Networks , 2015, ACL.

[10]  Heng Ji,et al.  Refining Event Extraction through Cross-Document Inference , 2008, ACL.

[11]  Jun Zhao,et al.  Collective Event Detection via a Hierarchical and Bias Tagging Networks with Gated Multi-level Attention Mechanisms , 2018, EMNLP.

[12]  Jun Zhao,et al.  Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks , 2015, ACL.

[13]  Ralph Grishman,et al.  Graph Convolutional Networks With Argument-Aware Pooling for Event Detection , 2018, AAAI.

[14]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[15]  Bin Ma,et al.  Using Cross-Entity Inference to Improve Event Extraction , 2011, ACL.

[16]  Zhiyuan Liu,et al.  Graph Neural Networks: A Review of Methods and Applications , 2018, AI Open.

[17]  Xiao Liu,et al.  Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation , 2018, EMNLP.

[18]  David Ahn,et al.  The stages of event extraction , 2006 .

[19]  Ralph Grishman,et al.  Modeling Skip-Grams for Event Detection with Convolutional Neural Networks , 2016, EMNLP.

[20]  Yue Zhao,et al.  Document Embedding Enhanced Event Detection with Hierarchical and Supervised Attention , 2018, ACL.

[21]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[22]  Dan Roth,et al.  Automatic Event Extraction with Structured Preference Modeling , 2012, ACL.

[23]  Ken-ichi Kawarabayashi,et al.  Representation Learning on Graphs with Jumping Knowledge Networks , 2018, ICML.