Named entity recognition (NER) is one fundamental task in natural language processing, which is usually viewed as a sequence labeling problem and typically addressed by neural conditional random field (CRF) models, such as BiLSTM-CRF. Intuitively, the entity types contain rich semantic information and the entity type sequence in a sentence can globally reflect the sentence-level semantics. However, most previous works recognize named entities based on the feature representation of each token in the input sentence, and the token-level features cannot capture the global-entity-type-related semantic information in the sentence. In this paper, we propose a joint model to exploit the global-type-related semantic information for NER. Concretely, we introduce a new auxiliary task, namely sentence-level entity type sequence prediction (TSP), to supervise and constrain the global feature representation learning process. Furthermore, a multitask learning method is used to integrate the global-type-related semantic information into the NER model. Experiments on the four datasets in different languages and domains show that our final model is highly effective, consistently outperforming the BiLSTM-CRF baseline and leading to competitive results on all datasets.

中文翻译：

---

一种通过全局利用句子级语义来识别命名实体的多任务学习方法

命名实体识别 (NER) 是自然语言处理中的一项基本任务，通常被视为序列标记问题，通常由神经条件随机场 (CRF) 模型解决，例如 BiLSTM-CRF。直观地说，实体类型包含丰富的语义信息，句子中的实体类型序列可以全局反映句子级语义。然而，之前的大多数工作都是基于输入句子中每个标记的特征表示来识别命名实体，而标记级特征无法捕获句子中与全局实体类型相关的语义信息。在本文中，我们提出了一种联合模型来利用 NER 的全局类型相关语义信息。具体来说，我们引入了一个新的辅助任务，即句子级实体类型序列预测（TSP），监督和约束全局特征表示学习过程。此外，使用多任务学习方法将全局类型相关的语义信息集成到 NER 模型中。对不同语言和领域的四个数据集的实验表明，我们的最终模型非常有效，始终优于 BiLSTM-CRF 基线，并在所有数据集上产生了具有竞争力的结果。