arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.15243cs.CL
收藏

无监督标签感知事件触发器和参数分类

Unsupervised Label-aware Event Trigger and Argument Classification

HKUST(香港科技大学);University of Pennsylvania(宾夕法尼亚大学)

Hongming Zhang, Haoyu Wang, Dan Roth

摘要:

识别事件并将它们映射到预定义的事件类型长期以来一直是重要的自然语言处理问题。大多数以前的工作一直严重依赖于劳动密集型和特定领域的注释,而忽略了事件类型的标签中包含的语义含义。因此,学习的模型不能有效地推广到新的领域,其中可能会引入新的事件类型。在本文中,我们提出了一个无监督的事件提取管道,它首先使用可用的工具(例如,SRL),然后自动映射到预定义的事件类型与我们提出的无监督分类模型。我们的模型不依赖于注释数据,而是将已识别事件的语义与事件类型标签的语义相匹配。具体来说,我们利用预先训练的语言模型来上下文地表示事件触发器和参数的预定义类型。在我们通过表示相似性将识别的事件映射到目标类型之后,我们使用事件本体(例如,自变量类型“Victim”只能作为事件类型“Attack”的自变量出现)作为全局约束来正则化预测。在ACE-2005数据集上进行测试时,该方法非常有效,该数据集有33个触发器和22个参数类型。在不使用任何注释的情况下,我们成功地将83%的触发器和54%的参数映射到正确的类型,几乎是以前zero-shot方法性能的两倍。

英文摘要:

Identifying events and mapping them to pre-defined event types has long been an important natural language processing problem. Most previous work has been heavily relying on labor-intensive and domain-specific annotations while ignoring the semantic meaning contained in the labels of the event types. As a result, the learned models cannot effectively generalize to new domains, where new event types could be introduced. In this paper, we propose an unsupervised event extraction pipeline, which first identifies events with available tools (e.g., SRL) and then automatically maps them to pre-defined event types with our proposed unsupervised classification model. Rather than relying on annotated data, our model matches the semantics of identified events with those of event type labels. Specifically, we leverage pre-trained language models to contextually represent pre-defined types for both event triggers and arguments. After we map identified events to the target types via representation similarity, we use the event ontology (e.g., argument type "Victim" can only appear as the argument of event type "Attack") as global constraints to regularize the prediction. The proposed approach is shown to be very effective when tested on the ACE-2005 dataset, which has 33 trigger and 22 argument types. Without using any annotation, we successfully map 83% of the triggers and 54% of the arguments to the correct types, almost doubling the performance of previous zero-shot approaches.

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。

↑