Recent work proposes a family of contextual embeddings that significantly improves the accuracy of sequence labelers over non-contextual embeddings. However, there is no definite conclusion on whether we can build better sequence labelers by combining different kinds of embeddings in various settings. In this paper, we conduct extensive experiments on 3 tasks over 18 datasets and 8 languages to study the accuracy of sequence labeling with various embedding concatenations and make three observations: (1) concatenating more embedding variants leads to better accuracy in rich-resource and cross-domain settings and some conditions of low-resource settings; (2) concatenating additional contextual sub-word embeddings with contextual character embeddings hurts the accuracy in extremely low-resource settings; (3) based on the conclusion of (1), concatenating additional similar contextual embeddings cannot lead to further improvements. We hope these conclusions can help people build stronger sequence labelers in various settings.
翻译:最近的工作提出了一系列背景嵌入,大大提高了序列标签标签相对于非传统嵌入的准确性。然而,对于我们能否通过将不同类型的嵌入组合在不同环境中建立更好的序列标签,我们并没有得出明确的结论。在本文件中,我们对18个数据集和8种语言的3项任务进行了广泛的实验,以研究与各种嵌入嵌入连接的序列标签的准确性,并提出3项观察:(1) 整合更多的嵌入变量,导致丰富资源和跨域设置以及低资源设置的某些条件更加准确;(2) 将新增的背景嵌入与背景字符嵌入的子词混为一体,伤害了极端低资源环境中的准确性;(3) 根据(1)的结论,将其他类似的背景嵌入组合无法导致进一步的改进。 我们希望这些结论能够帮助人们在不同环境中建立更强大的序列标签。