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

Amir Pouran Ben Veyseh,Tuan Ngo Nguyen,Thien Huu Nguyen

doi:10.18653/v1/2020.findings-emnlp.326

Abstract

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.

Highlights

Event Extraction (EE) is an important task of Information Extraction that aims to recognize events and their arguments in text
We introduce the mutual information between the generated representations of Graph Transformer Networks (GTNs) and the input sentences as an additional term in the overall loss function to improve the generalization of GTNs for Event Argument Extraction (EAE)
In order to improve the generalization, we propose to regularize the representation vectors obtained by GTN so only the effective information for EAE is preserved in the GTN representations for argument prediction and the nuisance information of the training data can be avoided

Summary

Introduction

Event Extraction (EE) is an important task of Information Extraction that aims to recognize events and their arguments in text. ED has been studied extensively with deep learning while EAE is relatively less explored (Wang et al, 2019b). The current state-of-the-art methods for EAE have involved deep learning models that compute an abstract representation vector for each word in the input sentences based on the information from the other context words. The representation vectors for the words are aggregated to perform EAE (Chen et al, 2015; Nguyen et al, 2016). Our main motivation in this work is to exploit different structures in the input sentences to improve the representation vectors for the words in the deep learning models for EAE. A sentence structure (or view) refers to an importance score matrix whose cells quantify the contribution of a context word for the representation vector computation of the current word for EAE. Consider the following sentence as an example: Iraqi Press constantly report interviews with Hussain Molem, the Hanif Bashir’s son-in-law, while US officials confirmed all Bashir’s family members were killed last week

Objectives

Methods

Results

Conclusion