命名实体识别作为依赖分析（CS CL）---用户7305506

命名实体识别（NER）是自然语言处理中的一项基本任务，它涉及到识别文本对实体的引用范围。净资产收益率研究通常只关注扁平实体（扁平净资产收益率），忽略了实体引用可以嵌套的事实，如[中国银行]（Finkel和Manning，2009）。在本文中，我们使用基于图的依赖解析的思想，通过biaffine模型为我们的模型提供输入的全局视图（Dozat和Manning，2017）。biaffine模型在一个句子中对开始和结束标记进行评分，我们使用这些标记来探索所有的跨度，这样模型就能够准确地预测命名实体。通过对8个语料库的测试，验证了该模型对嵌套式和扁平式NER的有效性，并在所有语料库上都取得了SoTA性能，准确率提高了2.2个百分点。

原文标题：Named Entity Recognition as Dependency Parsing

原文：Named Entity Recognition (NER) is a fundamental task in Natural Language Processing, concerned with identifying spans of text expressing references to entities. NER research is often focused on flat entities only (flat NER), ignoring the fact that entity references can be nested, as in [Bank of [China]] (Finkel and Manning, 2009). In this paper, we use ideas from graph-based dependency parsing to provide our model a global view on the input via a biaffine model (Dozat and Manning, 2017). The biaffine model scores pairs of start and end tokens in a sentence which we use to explore all spans, so that the model is able to predict named entities accurately. We show that the model works well for both nested and flat NER through evaluation on 8 corpora and achieving SoTA performance on all of them, with accuracy gains of up to 2.2 percentage points.

原文作者：Juntao Yu, Bernd Bohnet, Massimo Poesio

原文地址：https://arxiv.org/abs/2005.07150