缓解命名实体识别中的实体外错误：一种句子级策略
Mitigating Out-of-Entity Errors in Named Entity Recognition: A Sentence-Level Strategy
AI总结：
针对命名实体识别中的实体外问题，提出充分利用句子级信息的S+NER框架，结合模板上下文理解与对比学习优化表示，在5个基准数据集上优于部分现有先进模型。
摘要：
以往许多命名实体识别（NER）模型都存在实体外（OOE）问题，即测试样本实体提及中的词元未在训练样本中出现过，这阻碍了模型取得令人满意的性能。为提升OOE-NER性能，本文提出一种名为S+NER的新框架，该框架充分利用句子级信息。我们的S+NER能取得更优的OOE-NER性能，主要得益于以下两项特殊设计：1）首先借助一组模板，发挥预训练语言模型对目标实体句子级上下文的理解能力；2）随后通过对比学习策略和模板池化方法，基于正、负模板对句子级表示进行优化，以获得更好的NER结果。我们在5个基准数据集上开展的大量实验表明，S+NER的性能优于部分当前最先进的OOE-NER模型。
英文摘要：
Many previous models of named entity recognition (NER) suffer from the problem of Out-of-Entity (OOE), i.e., the tokens in the entity mentions of the test samples have not appeared in the training samples, which hinders the achievement of satisfactory performance. To improve OOE-NER performance, in this paper, we propose a new framework, namely S+NER, which fully leverages sentence-level information. Our S+NER achieves better OOE-NER performance mainly due to the following two particular designs. 1) It first exploits the pre-trained language model's capability of understanding the target entity's sentence-level context with a template set. 2) Then, it refines the sentence-level representation based on the positive and negative templates, through a contrastive learning strategy and template pooling method, to obtain better NER results. Our extensive experiments on five benchmark datasets have demonstrated that, our S+NER outperforms some state-of-the-art OOE-NER models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
