TL;DR应用预训练的基于字符的语言模型,成功提升了历史德语低资源命名实体识别准确性,并相较于经典 CRF-based 方法和 Bi-LSTMs,提高了高达 6% 的 F1 得分表现。
Abstract
Recent advances in language modeling using deep neural networks have shown
that these models learn representations, that vary with the network depth from
morphology to semantic relationships like co-reference. We