Graph Transformer Networks with Syntactic and Semantic Structures for Event Argument Extraction

The goal of Event Argument Extraction (EAE) is to find the role of each entity mention for a given event trigger word. It has been shown in the previous works that the syntactic structures of the sentences are helpful for the deep learning models for EAE. However, a major problem in such prior works is that they fail to exploit the semantic structures of the sentences to induce effective representations for EAE. Consequently, in this work, we propose a novel model for EAE that exploits both syntactic and semantic structures of the sentences with the Graph Transformer Networks (GTNs) to learn more effective sentence structures for EAE. In addition, we introduce a novel inductive bias based on information bottleneck to improve generalization of the EAE models. Extensive experiments are performed to demonstrate the benefits of the proposed model, leading to state-of-the-art performance for EAE on standard datasets.

[1]  Siddharth Patwardhan,et al.  A Unified Model of Phrasal and Sentential Evidence for Information Extraction , 2009, EMNLP.

[2]  Franck Dernoncourt,et al.  Extensively Matching for Few-shot Learning Event Detection , 2020, NUSE.

[3]  Xu Han,et al.  Adversarial Training for Weakly Supervised Event Detection , 2019, NAACL.

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

[5]  Dongsheng Li,et al.  Exploring Pre-trained Language Models for Event Extraction and Generation , 2019, ACL.

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

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

[8]  Yoshua Bengio,et al.  Learning deep representations by mutual information estimation and maximization , 2018, ICLR.

[9]  Jingyuan Zhang,et al.  A Question Answering-Based Framework for One-Step Event Argument Extraction , 2020, IEEE Access.

[10]  Jaewoo Kang,et al.  Graph Transformer Networks , 2019, NeurIPS.

[11]  Katrin Erk,et al.  Implicit Argument Prediction with Event Knowledge , 2018, NAACL.

[12]  Ralph Grishman,et al.  New York University 2016 System for KBP Event Nugget: A Deep Learning Approach , 2016, TAC.

[13]  Maosong Sun,et al.  HMEAE: Hierarchical Modular Event Argument Extraction , 2019, EMNLP.

[14]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[15]  Sophia Ananiadou,et al.  Comparable Study of Event Extraction in Newswire and Biomedical Domains , 2014, COLING.

[16]  Ralph Grishman,et al.  Filtered Ranking for Bootstrapping in Event Extraction , 2010, COLING.

[17]  Heng Ji,et al.  Joint Event Extraction via Structured Prediction with Global Features , 2013, ACL.

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

[19]  Mihai Surdeanu,et al.  Event Extraction as Dependency Parsing , 2011, ACL.

[20]  Jing Liu,et al.  RBPB: Regularization-Based Pattern Balancing Method for Event Extraction , 2016, ACL.

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

[22]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

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

[24]  End-to-End Entity and Event Extraction with Generative Adversarial Imitation Learning , 2018 .

[25]  Heng Ji,et al.  Improving Event Extraction via Multimodal Integration , 2017, ACM Multimedia.

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

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

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

[29]  Naftali Tishby,et al.  The information bottleneck method , 2000, ArXiv.

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

[31]  Yoshua Bengio,et al.  Mutual Information Neural Estimation , 2018, ICML.

[32]  Xiang Zhang,et al.  Automatically Labeled Data Generation for Large Scale Event Extraction , 2017, ACL.

[33]  Grace Hui Yang,et al.  Structured use of external knowledge for event-based open domain question answering , 2003, SIGIR.

[34]  Yiming Yang,et al.  CMU CS Event TAC-KBP2016 Event Argument Extraction System , 2016, TAC.

[35]  Andrew McCallum,et al.  Robust Biomedical Event Extraction with Dual Decomposition and Minimal Domain Adaptation , 2011, BioNLP@ACL.

[36]  Archna Bhatia,et al.  Improving DISCERN with Deep Learning , 2016, TAC.

[37]  Lifu Huang,et al.  Zero-Shot Transfer Learning for Event Extraction , 2017, ACL.

[38]  Thien Huu Nguyen,et al.  Event Detection: Gate Diversity and Syntactic Importance Scores for Graph Convolution Neural Networks , 2020, EMNLP.

[39]  Thien Huu Nguyen,et al.  One for All: Neural Joint Modeling of Entities and Events , 2018, AAAI.

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

[41]  Jian Liu,et al.  Event Detection via Gated Multilingual Attention Mechanism , 2018, AAAI.

[42]  Tom M. Mitchell,et al.  Joint Extraction of Events and Entities within a Document Context , 2016, NAACL.

[43]  James Ferguson,et al.  University of Washington TAC-KBP 2016 System Description , 2016, TAC.

[44]  Franck Dernoncourt,et al.  Exploiting the Matching Information in the Support Set for Few Shot Event Classification , 2020, PAKDD.

[45]  Zhiyi Song,et al.  Overview of Linguistic Resources for the TAC KBP 2017 Evaluations: Methodologies and Results , 2017, TAC.

[46]  Donghong Ji,et al.  Extracting Entities and Events as a Single Task Using a Transition-Based Neural Model , 2019, IJCAI.

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

[48]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.