基于对比学习与数据增强的零样本事件检测

A Zero-Shot Event Detection Model Based on Contrastive Learning and Data Augmentation

事件检测是一项经典的自然语言处理任务。然而在实践中,获取高质量的标注数据需要耗费大量的人力,这使得现有的基于监督学习的方法在面对大量未定义的新事件类型时表现不佳。面对零样本事件检测的困境,现有方法或者需要预定义的事件类型作为启发规则,或者由于自编码器类间特征提取能力不足,无法进一步归类发现的未知事件。为此,该文提出了一种基于对比学习与数据增强的零样本事件检测方法,通过对事件描述的重构与复写,自动为无监督的对比学习提供训练样本。模型只需要部分已知事件类别标准数据,便可以从大量文本中自动发现并归类新的事件类型。实验表明,该方法在保持对已知类别事件识别能力的同时,能够显著提升对未知事件类别识别的准确率。

Event detection is a classic natural language processing task.In practice,acquiring high-quality labelled data is labor-intensive,which makes existing supervised-learning-based methods underperform in dealing with large numbers of new,undefined event types.In this paper,we propose a zero-shot event detection model based on contrastive learning and data augmentation,which automatically provides training examples for unsupervised comparative learning by refactoring and rewriting event descriptions.Our model can automatically discover and categorize new event types from a large amount of text,which requires only a fraction of the standard data of known event categories.Experiments show that our approach can significantly improve the accuracy of identifying unknown event categories while maintaining the ability to identify known categories from events.