ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification

04/15/2022
by   Meiqi Chen, et al.
14

Document-level Event Causality Identification (DECI) aims to identify causal relations between event pairs in a document. It poses a great challenge of across-sentence reasoning without clear causal indicators. In this paper, we propose a novel Event Relational Graph TransfOrmer (ERGO) framework for DECI, which improves existing state-of-the-art (SOTA) methods upon two aspects. First, we formulate DECI as a node classification problem by constructing an event relational graph, without the needs of prior knowledge or tools. Second, ERGO seamlessly integrates event-pair relation classification and global inference, which leverages a Relational Graph Transformer (RGT) to capture the potential causal chain. Besides, we introduce edge-building strategies and adaptive focal loss to deal with the massive false positives caused by common spurious correlation. Extensive experiments on two benchmark datasets show that ERGO significantly outperforms previous SOTA methods (13.1 average). We have conducted extensive quantitative analysis and case studies to provide insights for future research directions (Section 4.8).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/03/2021

Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement

Current models for event causality identification (ECI) mainly adopt a s...
research
06/07/2022

RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction

In document-level event extraction (DEE) task, event arguments always sc...
research
04/15/2022

Towards Fine-grained Causal Reasoning and QA

Understanding causality is key to the success of NLP applications, espec...
research
09/01/2020

Visual Causality Analysis of Event Sequence Data

Causality is crucial to understanding the mechanisms behind complex syst...
research
02/19/2021

Back to Prior Knowledge: Joint Event Causality Extraction via Convolutional Semantic Infusion

Joint event and causality extraction is a challenging yet essential task...
research
06/03/2021

LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification

Modern models for event causality identification (ECI) are mainly based ...
research
03/04/2022

ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification

Generating new events given context with correlated ones plays a crucial...

Please sign up or login with your details

Forgot password? Click here to reset