Advancing Event Causality Identification via Heuristic Semantic Dependency Inquiry Network
This work addresses the challenge of identifying causal relations between events in texts, which is incremental as it builds on existing methods by focusing on semantic dependencies to overcome limitations in explicit clues and external knowledge bias.
The paper tackled the problem of Event Causality Identification (ECI) by proposing SemDI, a Semantic Dependency Inquiry Network that captures semantic dependencies and uses a Cloze Analyzer to infer causal relations, achieving state-of-the-art results on three benchmarks.
Event Causality Identification (ECI) focuses on extracting causal relations between events in texts. Existing methods for ECI primarily rely on causal features and external knowledge. However, these approaches fall short in two dimensions: (1) causal features between events in a text often lack explicit clues, and (2) external knowledge may introduce bias, while specific problems require tailored analyses. To address these issues, we propose SemDI - a simple and effective Semantic Dependency Inquiry Network for ECI. SemDI captures semantic dependencies within the context using a unified encoder. Then, it utilizes a Cloze Analyzer to generate a fill-in token based on comprehensive context understanding. Finally, this fill-in token is used to inquire about the causal relation between two events. Extensive experiments demonstrate the effectiveness of SemDI, surpassing state-of-the-art methods on three widely used benchmarks. Code is available at https://github.com/hrlics/SemDI.