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

10/26/2020
by   Amir Pouran Ben Veyseh, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/26/2020

Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning

Targeted opinion word extraction (TOWE) is a sub-task of aspect based se...
research
07/07/2019

Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures

Event factuality prediction (EFP) is the task of assessing the degree to...
research
12/05/2022

Syntactic Multi-view Learning for Open Information Extraction

Open Information Extraction (OpenIE) aims to extract relational tuples f...
research
11/05/2019

A Joint Model for Definition Extraction with Syntactic Connection and Semantic Consistency

Definition Extraction (DE) is one of the well-known topics in Informatio...
research
06/08/2022

Syntactic Inductive Biases for Deep Learning Methods

In this thesis, we try to build a connection between the two schools by ...
research
10/27/2020

Event Detection: Gate Diversity and Syntactic Importance Scoresfor Graph Convolution Neural Networks

Recent studies on event detection (ED) haveshown that the syntactic depe...
research
08/27/2022

A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneck

Event argument extraction (EAE) aims to extract arguments with given rol...

Please sign up or login with your details

Forgot password? Click here to reset