通过上下文填空机制，精准识别文本中事件的因果关系。
Advancing Event Causality Identification via Heuristic Semantic Dependency Inquiry Network
- 用统一编码器捕捉上下文语义依赖，再通过填空生成候选词。
- 在三个基准数据集上超越当前最佳方法，提升显著。
- 适合需要高精度因果推理的自然语言理解任务。
事件因果识别（ECI）旨在从文本中提取事件间的因果关系。现有方法主要依赖因果特征和外部知识，但在两个方面存在不足：(1) 文本中事件间的因果线索往往不明显；(2) 外部知识可能引入偏见，且特定问题需定制化分析。为此，我们提出SemDI——一种简洁有效的语义依赖询问网络用于ECI。SemDI使用统一编码器捕捉上下文中的语义依赖，随后通过填空分析器基于整体上下文理解生成填空标记。该标记被用来询问两个事件之间的因果关系。大量实验表明，SemDI在三个广泛使用的基准数据集上均优于当前最优方法。代码已开源：https://github.com/hrlics/SemDI。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。