论文标题
通过细心的句法信息合奏改进指定的实体识别
Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information
论文作者
论文摘要
命名的实体识别（NER）对句子句法和语义属性高度敏感，在该属性和语义属性中，可以根据其使用和放置在运行文本中提取实体。为了建模此类属性，可以依靠现有资源来为NER任务提供有用的知识；一些现有的研究证明了这样做的有效性，但在适当利用知识（例如在特定环境中区分重要知识）方面受到限制。在本文中，我们通过细心的集合利用不同类型的句法信息来改善NER，该集合通过提出的键值值存储网络，语法注意力以及分别编码，加权和汇总此类句法信息的栅极机制功能化。对六个英语和中文基准数据集的实验结果表明了该模型的有效性，并表明它表现优于所有实验数据集的先前研究。
Named entity recognition (NER) is highly sensitive to sentential syntactic and semantic properties where entities may be extracted according to how they are used and placed in the running text. To model such properties, one could rely on existing resources to providing helpful knowledge to the NER task; some existing studies proved the effectiveness of doing so, and yet are limited in appropriately leveraging the knowledge such as distinguishing the important ones for particular context. In this paper, we improve NER by leveraging different types of syntactic information through attentive ensemble, which functionalizes by the proposed key-value memory networks, syntax attention, and the gate mechanism for encoding, weighting and aggregating such syntactic information, respectively. Experimental results on six English and Chinese benchmark datasets suggest the effectiveness of the proposed model and show that it outperforms previous studies on all experiment datasets.
