Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning
Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning
复制标题
DOI：
10.48550/arxiv.2204.09589
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Kang Zhou;Yuepei Li;Qi Li
中科院分区：
文献类型：
--
作者：
Kang Zhou;Yuepei Li;Qi Li
本文研究了远程监督下的命名实体识别问题。由于外部词典和/或知识库的不完整性，这种远距离注释的训练数据通常遭受高的假阴性率。为此，我们制定了远程监督NER（DS-NER）的问题，通过多类积极和无标签（MPU）学习，并提出了一种理论和实践上新颖的CONFidence-based MPU（Conf-MPU）的方法。为了处理不完整的注释，Conf-MPU包括两个步骤。首先，为作为实体令牌的每个令牌估计置信度分数。然后，建议的Conf-MPU风险估计应用于训练多类分类器的NER任务。在两个由各种外部知识标记的基准数据集上的实验表明，所提出的Conf-MPU比现有的DS-NER方法的优越性。我们的代码可以在Github上找到。
In this paper, we study the named entity recognition (NER) problem under distant supervision. Due to the incompleteness of the external dictionaries and/or knowledge bases, such distantly annotated training data usually suffer from a high false negative rate. To this end, we formulate the Distantly Supervised NER (DS-NER) problem via Multi-class Positive and Unlabeled (MPU) learning and propose a theoretically and practically novel CONFidence-based MPU (Conf-MPU) approach. To handle the incomplete annotations, Conf-MPU consists of two steps. First, a confidence score is estimated for each token of being an entity token. Then, the proposed Conf-MPU risk estimation is applied to train a multi-class classifier for the NER task. Thorough experiments on two benchmark datasets labeled by various external knowledge demonstrate the superiority of the proposed Conf-MPU over existing DS-NER methods. Our code is available at Github.