论文标题
指定实体识别中未标记的实体问题的经验分析
Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition
论文作者
论文摘要
在许多情况下，指定的实体识别（NER）模型严重遭受了未标记的实体问题，句子的实体可能无法完全注释。通过对合成数据集进行的经验研究，我们发现了两种性能降解的原因。一种是减少注释实体，另一个是将未标记的实体视为负面实例。第一个原因比第二个原因少，可以通过采用预训练的语言模型来减轻。第二个原因严重误导了训练模型，并极大地影响了其表现。根据上述观察，我们提出了一种一般方法，该方法几乎可以消除未标记实体带来的误导。关键思想是使用负面抽样，在很大程度上避免了具有未标记实体的训练NER模型。合成数据集和现实世界数据集的实验表明，我们的模型对未标记的实体问题具有鲁棒性，并且超过了先前的基线。在宣布良好的数据集上，我们的模型具有最新方法的竞争力。
In many scenarios, named entity recognition (NER) models severely suffer from unlabeled entity problem, where the entities of a sentence may not be fully annotated. Through empirical studies performed on synthetic datasets, we find two causes of performance degradation. One is the reduction of annotated entities and the other is treating unlabeled entities as negative instances. The first cause has less impact than the second one and can be mitigated by adopting pretraining language models. The second cause seriously misguides a model in training and greatly affects its performances. Based on the above observations, we propose a general approach, which can almost eliminate the misguidance brought by unlabeled entities. The key idea is to use negative sampling that, to a large extent, avoids training NER models with unlabeled entities. Experiments on synthetic datasets and real-world datasets show that our model is robust to unlabeled entity problem and surpasses prior baselines. On well-annotated datasets, our model is competitive with the state-of-the-art method.
