【摘要】 事件同指消解是一个具有挑战性的自然语言处理任务，它在事件抽取、问答系统和阅读理解等任务中发挥着重要作用。现存的事件同指消解语料库的一个问题是标注规模较小，无法训练出高效能的模型。为了解决上述问题，该文提出了一个基于跨语言数据增强的事件同指消解神经网络模型ECR＿CDA(Event Coreference Resolution on Cross-lingual Data Augmentation)。该模型通过中英文语料互译来增强语料，并通过共享模型参数的方式实现中英文模型的跨语言学习，从而提高了事件同指消解的性能。在ACE 2005英文语料上的实验结果表明，ECR＿CDA优于目前最先进的基准系统。更多还原

【Abstract】 Event coreference resolution is a challenging task with wide application in event extraction, QA system, and reading comprehension. The best use the existing small-scale public corpus, this paper introduces a neural network model ECR＿CDA based on cross-lingual data augmentation. This model enhances the corpus through the translation of Chinese and English corpus, and improves the performance of event coreference resolution via the cross-lingual learning of Chinese and English models by sharing the model parameters. The experimental results on ACE 2005 English test set show that ECR＿CDA is superior to the most advanced baseline.更多还原