基于原型摊销条件随机场的Few-Shot事件检测
Few-Shot Event Detection with Prototypical Amortized Conditional Random Field
摘要:
当需要用少量样本识别新的事件类型时,事件检测往往会遇到困难。以往的工作试图通过先识别再分类的方式解决这个问题,但忽略了事件类型之间的触发差异,从而遭受错误传播。在本文中,我们提出了一种新的统一模型,将任务转换为一个Few-Shot标记问题的双部分标记计划。为此,我们首先提出了原型摊销条件随机场(PA-CRF)模型的标签依赖在Few-Shot的情况下,它近似的标签之间的转换分数的基础上的标签原型。然后,高斯分布的过渡分数建模,以减轻不确定的估计所造成的数据不足。实验结果表明,统一模型的工作优于现有的识别,然后分类模型和我们的PA-CRF进一步取得了最好的结果在基准数据集FewEvent。我们的代码和数据可在http://github.com/congxin95/PA-CRF上获得。
英文摘要:
Event detection tends to struggle when it needs to recognize novel event types with a few samples. The previous work attempts to solve this problem in the identify-then-classify manner but ignores the trigger discrepancy between event types, thus suffering from the error propagation. In this paper, we present a novel unified model which converts the task to a few-shot tagging problem with a double-part tagging scheme. To this end, we first propose the Prototypical Amortized Conditional Random Field (PA-CRF) to model the label dependency in the few-shot scenario, which approximates the transition scores between labels based on the label prototypes. Then Gaussian distribution is introduced for modeling of the transition scores to alleviate the uncertain estimation resulting from insufficient data. Experimental results show that the unified models work better than existing identify-then-classify models and our PA-CRF further achieves the best results on the benchmark dataset FewEvent. Our code and data are available at http://github.com/congxin95/PA-CRF.
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。