ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification
It addresses the challenge of identifying causal relations between events across sentences in documents, which is important for natural language processing applications, but is incremental as it builds on existing methods.
The paper tackles document-level event causality identification by proposing the ERGO framework, which formulates it as a node classification problem using an event relational graph and integrates relation classification with global inference, achieving a 13.1% average F1 gain over previous state-of-the-art methods.
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% F1 gains on average). We have conducted extensive quantitative analysis and case studies to provide insights for future research directions (Section 4.8).