论文标题
使用话语感知伯特的细粒度信息状态分类
Fine-grained Information Status Classification Using Discourse Context-Aware BERT
论文作者
论文摘要
以前关于桥接图表识别的工作（Hou等，2013a）将问题视为学习细粒度信息状态的子任务（IS）。但是，这些系统在很大程度上取决于许多手工制作的语言特征。在本文中，我们提出了一个简单的话语上下文感知的BERT模型，用于分类。在Isnotes语料库（Markert等，2012）上，我们的模型在细粒度上实现了新的最新性能是分类，与Hou等人相比，获得了4.8的绝对总体准确性提高。 （2013a）。更重要的是，我们还显示了10.5 f1点的改进，用于桥接图谱识别，而无需使用任何用于捕获桥接现象的复杂手工制作的语义特征。我们进一步分析了受过训练的模型，并发现每种IS类别的参与信号与信息状态的语言概念很好。
Previous work on bridging anaphora recognition (Hou et al., 2013a) casts the problem as a subtask of learning fine-grained information status (IS). However, these systems heavily depend on many hand-crafted linguistic features. In this paper, we propose a simple discourse context-aware BERT model for fine-grained IS classification. On the ISNotes corpus (Markert et al., 2012), our model achieves new state-of-the-art performance on fine-grained IS classification, obtaining a 4.8 absolute overall accuracy improvement compared to Hou et al. (2013a). More importantly, we also show an improvement of 10.5 F1 points for bridging anaphora recognition without using any complex hand-crafted semantic features designed for capturing the bridging phenomenon. We further analyze the trained model and find that the most attended signals for each IS category correspond well to linguistic notions of information status.
