arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.07615cs.CL
收藏

P4E:基于Few-Shot的事件检测方法

P4E: Few-Shot Event Detection as Prompt-Guided Identification and Localization

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Microsoft Research(微软研究院);Carnegie Mellon University(卡内基梅隆大学)

Sha Li, Liyuan Liu, Yiqing Xie, Heng Ji, Jiawei Han

摘要:

我们提出了P4E,一个识别和本地化的事件检测框架,集成了最好的Few-Shot提示和结构化预测。我们的框架分解成一个识别任务和定位任务的事件检测。对于识别任务,我们将其制定为多标签分类,我们利用基于完形填空的提示将我们的目标与语言模型的预训练任务相一致,使我们的模型能够快速适应新的事件类型。然后,我们采用一个事件类型不可知序列标记模型本地化的事件触发条件的识别输出。这种异构模型设计允许P4E快速学习新的事件类型,而不会牺牲进行结构化预测的能力。我们的实验证明了我们提出的设计的有效性,和P4 E表现出优越的性能为Few-Shot事件检测基准数据集FewEvent和MAVEN和SOTA的性能相当的ACE上的全监督事件检测。

英文摘要:

We propose P4E, an identify-and-localize event detection framework that integrates the best of few-shot prompting and structured prediction. Our framework decomposes event detection into an identification task and a localization task. For the identification task, which we formulate as multi-label classification, we leverage cloze-based prompting to align our objective with the pre-training task of language models, allowing our model to quickly adapt to new event types. We then employ an event type-agnostic sequence labeling model to localize the event trigger conditioned on the identification output. This heterogeneous model design allows P4E to quickly learn new event types without sacrificing the ability to make structured predictions. Our experiments demonstrate the effectiveness of our proposed design, and P4E shows superior performance for few-shot event detection on benchmark datasets FewEvent and MAVEN and comparable performance to SOTA for fully-supervised event detection on ACE.

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。

↑