论文标题
级联模型，用于更好的细粒度命名实体识别
Cascaded Models for Better Fine-Grained Named Entity Recognition
论文作者
论文摘要
命名实体识别（NER）是许多自然语言应用（例如关系提取或事件提取）的必不可少的前体任务。许多NER研究都在具有很少类型的实体类型（例如PER，LOC，ORG，MISC）的数据集上进行，但是许多现实世界的应用程序（救灾，复杂的事件提取，执法）可以从较大的NER排版中受益。最近，创建了数百至数千种实体的数据集，引发了新的研究线（Sekine，2008; Ling and Weld，2012; Gillick et al。，2014; Choiet al。，2018）。在本文中，我们提出了一种标记细颗粒NER的级联方法，该方法适用于在TAC KBP 2019评估中使用的新发布的细粒NER数据集（Ji等，2019），灵感来自一些粗标签的训练数据。通过使用变压器网络的组合，我们表明性能可以提高约20 f1绝对功能，而与完整的细粒类型建立的直接模型相比，它可以表明，令人惊讶的是，使用三种语言的课程标记数据可以改善英语数据。
Named Entity Recognition (NER) is an essential precursor task for many natural language applications, such as relation extraction or event extraction. Much of the NER research has been done on datasets with few classes of entity types (e.g. PER, LOC, ORG, MISC), but many real world applications (disaster relief, complex event extraction, law enforcement) can benefit from a larger NER typeset. More recently, datasets were created that have hundreds to thousands of types of entities, sparking new lines of research (Sekine, 2008;Ling and Weld, 2012; Gillick et al., 2014; Choiet al., 2018). In this paper we present a cascaded approach to labeling fine-grained NER, applying to a newly released fine-grained NER dataset that was used in the TAC KBP 2019 evaluation (Ji et al., 2019), inspired by the fact that training data is available for some of the coarse labels. Using a combination of transformer networks, we show that performance can be improved by about 20 F1 absolute, as compared with the straightforward model built on the full fine-grained types, and show that, surprisingly, using course-labeled data in three languages leads to an improvement in the English data.
