We introduce a new scientific named entity recognizer called SEPT, which stands for Span Extractor with Pre-trained Transformers. In recent papers, span extractors have been demonstrated to be a powerful model compared with sequence labeling models. However, we discover that with the development of pre-trained language models, the performance of span extractors appears to become similar to sequence labeling models. To keep the advantages of span representation, we modified the model by under-sampling to balance the positive and negative samples and reduce the search space. Furthermore, we simplify the origin network architecture to combine the span extractor with BERT. Experiments demonstrate that even simplified architecture achieves the same performance and SEPT achieves a new state of the art result in scientific named entity recognition even without relation information involved.

翻译：我们引入了一个新的科学名称实体识别器,名为SEPT,它代表Span 抽取器,与受过训练的变异器相配。在最近的论文中,抽取器被证明与序列标签模型相比是一种强大的模型。然而,我们发现,随着预先训练的语言模型的开发,抽取器的性能似乎与序列标签模型相似。为了保持跨度代表的优势,我们通过低抽样来修改模型,以平衡正和负样本,并缩小搜索空间。此外,我们简化了源网络结构,将抽取器与BERT结合起来。实验表明,即使是简化的架构也能取得同样的性能,而SPT也实现了艺术成果的新状态,即使没有涉及相关信息,也实现了科学命名实体的承认。