论文标题
通过基于置信的多级积极和未标记的学习，远距离监督指定的实体识别
Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning
论文作者
论文摘要
在本文中，我们在遥远的监督下研究了指定的实体识别（NER）问题。由于外部字典和/或知识库的不完整，这种遥远注释的训练数据通常会遭受高误资率。为此，我们通过多级积极和未标记的学习（MPU）学习制定了遥远监督的NER（DS-NER）问题，并提出了一种理论上和实际的基于置信度的MPU（CONF MPU）方法。为了处理不完整的注释，Conf-MPU由两个步骤组成。首先，估计作为实体令牌的每个令牌的置信度得分。然后，提出的COND-MPU风险估计用于培训多级分类器以进行NER任务。通过各种外部知识标记的两个基准数据集进行了彻底的实验，证明了所提出的COND-MPU优于现有DS-NER方法。
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.
