arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.13621cs.CLcs.AIcs.IR
收藏

通过启发式语义依赖探究网络推进事件因果关系识别

Advancing Event Causality Identification via Heuristic Semantic Dependency Inquiry Network

College of Computer Science, Sichuan University(四川大学计算机学院)

Haoran Li, Qiang Gao, Hongmei Wu, Li Huang

AI总结:

针对ECI中因果线索缺失与外部知识偏差问题,提出SemDI网络,通过统一编码器和完形填空分析器生成词元以判断事件因果关系,并在三个基准上超越现有方法。

摘要:

事件因果关系识别(ECI)专注于抽取文本中事件之间的因果关系。现有ECI方法主要依赖因果特征和外部知识。然而,这些方法在两个方面存在不足:(1)文本中事件之间的因果特征往往缺乏显式线索;(2)外部知识可能引入偏差,而特定问题需要量身定制的分析。为解决这些问题,我们提出了SemDI——一个用于ECI的简单且有效的语义依赖探究网络。SemDI使用统一编码器捕获上下文中的语义依赖。然后,它利用完形填空分析器(Cloze Analyzer)基于对上下文的全面理解生成一个填充词元。最后,该填充词元被用于探究两个事件之间的因果关系。大量实验证明了SemDI的有效性,其在三个广泛使用的基准测试上超越了最先进方法。代码可在https://github.com/hrlics/SemDI获取。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑