解决实体识别中未见实体词的错误，通过句子级上下文提升模型泛化能力。
Mitigating Out-of-Entity Errors in Named Entity Recognition: A Sentence-Level Strategy
- 利用模板集与预训练模型捕捉句子级上下文信息。
- 通过对比学习和模板聚合优化表示，显著提升未见实体识别效果。
- 在五个数据集上超越现有先进模型，适合处理开放域实体识别任务。
许多先前的命名实体识别（NER）模型存在外源实体（OOE）问题，即测试样本中的实体词在训练中未出现，导致性能受限。为改善OOE-NER表现，本文提出新框架S+NER，充分挖掘句子级信息。S+NER主要基于两项设计：首先，利用预训练语言模型结合模板集理解目标实体的句子级上下文；其次，通过对比学习与模板池化策略，对句子级表示进行精炼，获得更优的NER结果。在五个基准数据集上的大量实验表明，S+NER优于部分当前最先进的OOE-NER模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。