For Named Entity Recognition (NER), sequence labeling-based and span-based paradigms are quite different. Previous research has demonstrated that the two paradigms have clear complementary advantages, but few models have attempted to leverage these advantages in a single NER model as far as we know. In our previous work, we proposed a paradigm known as Bundling Learning (BL) to address the above problem. The BL paradigm bundles the two NER paradigms, enabling NER models to jointly tune their parameters by weighted summing each paradigm's training loss. However, three critical issues remain unresolved: When does BL work? Why does BL work? Can BL enhance the existing state-of-the-art (SOTA) NER models? To address the first two issues, we implement three NER models, involving a sequence labeling-based model--SeqNER, a span-based NER model--SpanNER, and BL-NER that bundles SeqNER and SpanNER together. We draw two conclusions regarding the two issues based on the experimental results on eleven NER datasets from five domains. We then apply BL to five existing SOTA NER models to investigate the third issue, consisting of three sequence labeling-based models and two span-based models. Experimental results indicate that BL consistently enhances their performance, suggesting that it is possible to construct a new SOTA NER system by incorporating BL into the current SOTA system. Moreover, we find that BL reduces both entity boundary and type prediction errors. In addition, we compare two commonly used labeling tagging methods as well as three types of span semantic representations.
翻译:对于命名实体识别(NER)来说,基于标签的顺序和基于跨区域的范式是完全不同的。以前的研究表明,这两个范式具有明显的互补优势,但就我们所知,很少有模式试图在单一的净化模型中利用这些优势。在先前的工作中,我们提出了一个称为Bunbling Learning(BL)的范式,以解决上述问题。BL范式将两个净化模式捆绑在一起,使净化模式能够通过加权地计算每个范式的培训损失来联合调整其参数。然而,三个关键问题仍未解决:BL何时工作?为什么BL工作?为什么BL工作?BL能否加强现有的最新水平的NER模型?但就我们所知的单一净化模式而言,很少有模型试图将这些优势运用在单一的净化模型中加以利用。我们随后将目前的最新水平(SONER) 类型(SONER) 类型(SOL) 的运行模式分为两个不同的SOTAR 模型,我们用两个基于我们实验结果的两个问题得出了两个结论。我们用的是从五个域域的三套NER 来将SOL(BL) ASeral) 。我们用了一个Seral Bal(BL) laveal) laveal) laveal lax(B) lax (B) lax) laveal) lax) lax (B) lax) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B) (B)