Modern models for event causality identification (ECI) are mainly based on supervised learning, which are prone to the data lacking problem. Unfortunately, the existing NLP-related augmentation methods cannot directly produce the available data required for this task. To solve the data lacking problem, we introduce a new approach to augment training data for event causality identification, by iteratively generating new examples and classifying event causality in a dual learning framework. On the one hand, our approach is knowledge-guided, which can leverage existing knowledge bases to generate well-formed new sentences. On the other hand, our approach employs a dual mechanism, which is a learnable augmentation framework and can interactively adjust the generation process to generate task-related sentences. Experimental results on two benchmarks EventStoryLine and Causal-TimeBank show that 1) our method can augment suitable task-related training data for ECI; 2) our method outperforms previous methods on EventStoryLine and Causal-TimeBank (+2.5 and +2.1 points on F1 value respectively).
翻译:现代事件因果关系识别模式(ECI)主要基于监督学习,这容易造成缺乏数据的问题。不幸的是,现有的与NLP有关的增强方法无法直接产生这项任务所需的可用数据。为解决缺乏数据的问题,我们引入了一种新的方法,通过在双重学习框架内反复生成新实例和对事件因果关系进行分类,来增加事件因果关系识别培训数据。一方面,我们的方法以知识为导向,能够利用现有的知识基础生成完善的新句子。另一方面,我们的方法采用双重机制,这是一个可学习的增强框架,可以交互调整生成过程,生成与任务相关的句子。两个基准的实验结果显示:事件链和Causal-TimeBank 显示:(1) 我们的方法可以增加与事件链和Causal-TimeBank 相关的适当任务培训数据;(2)我们的方法优于以往关于事件链和Causal-TimeBank 的方法(分别是F1值的+2.5和+2.1点 )。